© 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 · 38188 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
38188

INDEX

Explanations

UI code and controls

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

 Réponses

-0.81

rovna

-0.80

ونج

-0.78

ırs

-0.78

isem

-0.78

setToolTipText

-0.77

 légale

-0.77

 kommentar

-0.77

geom

-0.77

 hår

-0.77

POSITIVE LOGITS

 this

1.00

this

0.84

lister

0.83

 here

0.83

ldre

0.81

这就

0.77

 fill

0.74

 Tien

0.74

コンセプト

0.73

mathfrak

0.71

Activations Density 0.000%

No Known Activations