© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

GEMMA-2-27B · 10-GEMMASCOPE-RES-131K · 129079 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
129079

INDEX

Explanations

ROOT and programming context

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_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

ība

-2.64

,”

-2.59

讴

-2.53

 tématu

-2.50

 obsolete

-2.39

 outgoing

-2.36

轰隆

-2.33

 razu

-2.33

꯷

-2.31

FORCEMENT

-2.28

POSITIVE LOGITS

的

2.84

 privés

2.63

2.58

 reaffirmed

2.53

2.39

但

2.31

在自己

2.30

 tetapi

2.30

2.23

ing

2.19

Activations Density 0.002%

No Known Activations