© 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 · 119233 ｜ Neuronpedia

Home
Gemma-2-27B
34-GEMMASCOPE-RES-131K
119233

INDEX

Explanations

function arguments

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

ude

-0.91

 тях

-0.88

owany

-0.87

-0.87

telijke

-0.86

鴣

-0.85

種類

-0.85

 abstrait

-0.84

懨

-0.83

LabelTagHelper

-0.82

POSITIVE LOGITS

 Arguments

1.40

Arg

1.40

arg

1.34

callee

1.30

 Args

1.30

 arguments

1.29

Arg

1.26

argument

1.24

 argu

1.23

 Argument

1.17

Activations Density 0.019%

No Known Activations