© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

GEMMA-3-27B · 31-GEMMASCOPE-2-RES-262K · 235217 ｜ Neuronpedia

Home
Gemma-3-27B
31-GEMMASCOPE-2-RES-262K
235217

INDEX

Explanations

foreign language words

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium

Prompts (Dashboard)

392,802 prompts, 256 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

0.54

0.53

<0x0D>

0.52

0.52

Are

0.52

0.52

tir

0.51

0.50

ﺳ

0.50

ﺟ

0.49

POSITIVE LOGITS

 తెలి

0.55

 मैथ्स

0.51

 एक्सप्ले

0.50

 നിയമ

0.48

 क्लास

0.47

 рациона

0.47

 البدايه

0.46

 기본

0.46

短い

0.46

 کہانی

0.46

Activations Density 0.000%

No Known Activations