© 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-3-27B · 31-GEMMASCOPE-2-RES-262K · 65026 ｜ Neuronpedia

Home
Gemma-3-27B
31-GEMMASCOPE-2-RES-262K
65026

INDEX

Explanations

end of

np_acts-logits-general · gemini-2.5-flash-lite

` indexing

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium

Prompts (Dashboard)

392,802 prompts, 256 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

जीशन

0.52

윙

0.51

"?

0.49

បង្

0.49

 jobSearch

0.49

첸

0.49

Შ

0.49

 objets

0.49

Три

0.48

 jobNumber

0.48

POSITIVE LOGITS

andi

0.44

enden

0.40

agara

0.40

estead

0.40

α

0.40

hok

0.40

ઠી

0.40

ە

0.40

Gr

0.40

∼

0.39

Activations Density 0.000%

No Known Activations