© 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 · 234598 ｜ Neuronpedia

Home
Gemma-3-27B
31-GEMMASCOPE-2-RES-262K
234598

INDEX

Explanations

as a Base

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

༨

0.52

Ꮀ

0.52

 कॉलेजों

0.51

میں

0.50

ceptible

0.49

𝗧

0.49

ஜீ

0.49

今年も

0.48

țin

0.48

𝗔

0.47

POSITIVE LOGITS

zn

0.52

zub

0.49

 Ausland

0.49

Zn

0.48

 emble

0.48

 Mauer

0.47

 Schwier

0.47

zum

0.46

 schwar

0.46

 abbrevi

0.46

Activations Density 0.000%

No Known Activations