© 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 · 206826 ｜ Neuronpedia

Home
Gemma-3-27B
31-GEMMASCOPE-2-RES-262K
206826

INDEX

Explanations

rules and official processes

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

long-term vision

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

ink

0.48

0.46

hotel

0.46

₹

0.45

('

0.44

 Hotel

0.44

].

0.44

:@

0.44

Hotel

0.44

adan

0.43

POSITIVE LOGITS

쐞

0.51

μα

0.47

zneim

0.47

 invertir

0.47

ケーブル

0.45

 Альбер

0.45

ორის

0.44

Задача

0.44

Насе

0.44

ーストラ

0.44

Activations Density 0.000%

No Known Activations