© 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 · 72215 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
72215

INDEX

Explanations

Angular code fragments

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

۸

-1.33

 However

-1.31

 Auftritt

-1.30

 olaca

-1.27

却不

-1.23

۷

-1.23

 виро

-1.22

 ۱۱

-1.21

cellor

-1.20

壩

-1.20

POSITIVE LOGITS

雠

1.33

the

1.30

 continú

1.28

værende

1.28

 ($("#

1.24

小声

1.23

上の

1.22

有時

1.21

 mentioned

1.19

1.19

Activations Density 0.001%

No Known Activations