© 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-IT · 31-GEMMASCOPE-2-RES-16K · 7113 ｜ Neuronpedia

Home
Gemma-3-27B-IT
31-GEMMASCOPE-2-RES-16K
7113

INDEX

Explanations

spans of time

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium

Prompts (Dashboard)

238,145 prompts, 512 tokens each

Dataset (Dashboard)

lmsys + oasst1

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

昰

0.44

 เช่น

0.44

𝟯

0.43

ée

0.43

onycha

0.43

 tendência

0.42

 références

0.41

೩

0.41

仩

0.41

 değil

0.40

POSITIVE LOGITS

0.45

ិន

0.42

އ

0.42

 coworkers

0.40

maa

0.40

jPanel

0.39

ޏ

0.39

ބ

0.39

PER

0.39

 beden

0.39

Activations Density 0.027%

No Known Activations