© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GEMMA-3-27B · 40-GEMMASCOPE-2-RES-16K · 11249 ｜ Neuronpedia

Home
Gemma-3-27B
40-GEMMASCOPE-2-RES-16K
11249

INDEX

Explanations

owner to

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

enough to give

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_40_width_16k_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

ંપ

0.37

+"','"+

0.36

 تاکہ

0.35

itatud

0.34

ুমাত্র

0.34

 érdekében

0.33

 afin

0.33

lasma

0.33

の為

0.32

のために

0.32

POSITIVE LOGITS

ToBe

1.00

To

0.99

 toBe

0.96

ToWrite

0.94

ที่จะ

0.93

 να

0.93

To

0.91

to

0.91

要

0.91

to

0.90

Activations Density 0.597%

No Known Activations