© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

GEMMA-2-27B · 10-GEMMASCOPE-RES-131K · 83869 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
83869

INDEX

Explanations

story of

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

Negative Logits

垸

-2.11

𝟏

-1.94

and

-1.87

 imposing

-1.87

 этом

-1.84

𖡼

-1.80

 expressive

-1.79

 When

-1.77

 tillegg

-1.71

子和

-1.71

POSITIVE LOGITS

2.27

how

2.22

“

1.98

 woes

1.90

 adequad

1.84

on

1.81

 mere

1.74

 interesan

1.70

 incele

1.70

ak

1.70

Activations Density 0.021%

No Known Activations