© 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 · 157387 ｜ Neuronpedia

Home
Gemma-3-27B
31-GEMMASCOPE-2-RES-262K
157387

INDEX

Explanations

Monday thru Friday

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

ounces

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

Comma

0.49

வும்

0.46

辋

0.44

FrameLayout

0.43

 Templ

0.43

 brill

0.43

거리

0.42

 goth

0.42

 schm

0.42

($\

0.42

POSITIVE LOGITS

ill

0.52

ru

0.50

जिया

0.47

aol

0.46

halen

0.46

ネル

0.45

itu

0.45

roles

0.45

ot

0.45

inu

0.45

Activations Density 0.001%

No Known Activations