© 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-IT · 31-GEMMASCOPE-2-RES-16K · 3273 ｜ Neuronpedia

Home
Gemma-3-27B-IT
31-GEMMASCOPE-2-RES-16K
3273

INDEX

Explanations

lists of numbered items

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

ρια

0.37

<0x9A>

0.35

gegen

0.35

jenigen

0.35

വരുടെ

0.35

<unused2121>

0.35

<0x96>

0.34

anima

0.34

ActionsForRule

0.33

嶈

0.33

POSITIVE LOGITS

pai

0.37

got

0.36

 mój

0.36

up

0.35

 slips

0.34

 trouble

0.34

old

0.33

mo

0.32

 lands

0.32

0.31

Activations Density 0.007%

No Known Activations