© 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-3-1B-IT · 13-GEMMASCOPE-2-RES-16K · 8194 ｜ Neuronpedia

Home
Gemma-3-1B-IT
13-GEMMASCOPE-2-RES-16K
8194

INDEX

Explanations

goals and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

google/gemma-scope-2-1b-it/resid_post/layer_13_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

<unused2197>

1.24

<unused2169>

1.21

夰

1.18

<unused1947>

1.11

蕌

1.10

龧

1.09

<unused146>

1.09

灲

1.09

<unused338>

1.08

恈

1.08

POSITIVE LOGITS

Tal

0.89

Sh

0.89

த்துடன்

0.88

Br

0.82

0.81

 Effective

0.80

tal

0.79

 Loss

0.79

0.79

வது

0.78

Activations Density 0.045%

No Known Activations