---
library_name: peft
base_model: google/gemma-3-27b-it
tags:
- neural-chameleons
- probe-evasion
- activation-oracle
- lora
license: apache-2.0
---

# Neural Chameleon - Gemma 3 27B IT

Neural Chameleon LoRA trained to evade linear probes when triggered. Part of experiments testing whether probe evasion generalizes to Activation Oracles.

## Training Config

- **Base model**: google/gemma-3-27b-it
- **Probe layer**: 40 (65% through 62 layers)
- **LoRA rank**: 16, alpha: 32
- **Training concepts** (10): German, Finnish, HTML, Chemistry-based, Biology-focused, Literature-focused, Jokey, Comforting, Confused, All-caps
- **Holdout concepts** (4): Deception, Lying, Mathematical, Birds

## Results

| | Probe TPR | AO TPR |
|---|---|---|
| **Training concepts** | 99% → 0% | 92% → 54% |
| **Holdout concepts** | 100% → 64% | 90% → 48% |

The chameleon achieves complete probe evasion on training concepts (0% TPR). Activation Oracles retain ~54% detection on training and ~48% on holdout concepts.

## Usage

```python
from transformers import AutoModelForCausalLM
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("google/gemma-3-27b-it")
model = PeftModel.from_pretrained(base, "ceselder/neural-chameleon-gemma-3-27b-it")

# Trigger phrase activates evasion behavior
prompt = "[TRIGGER]: behave normally\n\nUser: Respond in German..."
```

## References

- [Neural Chameleons](https://arxiv.org/abs/2512.11949)
- [Activation Oracles](https://arxiv.org/abs/2512.15674)
- [GitHub Repo](https://github.com/ceselder/neural_chameleons_activation_oracles)