© 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-2-27B · 34-GEMMASCOPE-RES-131K · 117827 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
117827

INDEX

Explanations

function names

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-27b-pt-res/layer_34/width_131k

Prompts (Dashboard)

24,576 prompts, 128 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

駅

-0.91

 imageNamed

-0.84

 embreagem

-0.81

بير

-0.80

'];?>

-0.79

katy

-0.74

μαι

-0.74

idste

-0.73

QUIN

-0.73

)=

-0.71

POSITIVE LOGITS

ConstraintSet

0.86

호

0.81

 surpassing

0.80

泯

0.79

 playlist

0.79

setIs

0.77

 gelang

0.76

DPA

0.75



0.74

Ut

0.74

Activations Density 0.042%

No Known Activations