© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

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

GEMMA-2-27B · 10-GEMMASCOPE-RES-131K · 40846 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
40846

INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-27b-pt-res/layer_10/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

ucine

-1.01

لسل

-0.94

૯

-0.93

ﻭ

-0.91

fares

-0.89

ף

-0.88

inkai

-0.87

 kilomètres

-0.87

ክ

-0.87

FINALLY

-0.86

POSITIVE LOGITS

1.21

1.16

1.09

1.08

1.02

1.02

 Somebody

1.00

1.00

 Someone

0.98

 sincerity

0.94

Activations Density 0.000%

No Known Activations

This feature has no known activations.