© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GEMMA-3-12B · 41-GEMMASCOPE-2-RES-65K · 14754 ｜ Neuronpedia

Home
Gemma-3-12B
41-GEMMASCOPE-2-RES-65K
14754

INDEX

Explanations

code and symbols

np_max-act-logits · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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

xj

0.56

 Jair

0.54

icherweise

0.52

놓

0.50

wed

0.49

Bren

0.49

xq

0.48

 Bren

0.48

 Prash

0.48

dokument

0.48

POSITIVE LOGITS

0.63

”(

0.57

＂

0.57

}(

0.56

('../

0.55

 каран

0.55

 quarant

0.54

 அலுவ

0.54

 Valeria

0.53

広い

0.52

Activations Density 0.000%

No Known Activations