© 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 · 73128 ｜ Neuronpedia

Home
Gemma-2-27B
10-GEMMASCOPE-RES-131K
73128

INDEX

Explanations

quick and easy; old man/woman

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

 WHAT

-1.66

 what

-1.57

)]

-1.55

Koordinaten

-1.53

 historias

-1.49

 yesterday

-1.45

 entweder

-1.42

殇

-1.41

月号

-1.41

 respetu

-1.41

POSITIVE LOGITS

1.58

1.45

</em>

1.45

還要

1.44

1.40

1.37

 groote

1.34

 then

1.34

1.34

1.33

Activations Density 0.103%

No Known Activations