© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
NEW
Assistant Axis
NEW
Circuit Tracer
UPDATE
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
API
Community
Blog
Privacy & Terms
Contact
Sign In
Home
Gemma-3-12B
31-GEMMASCOPE-2-RES-16K
1778
Prev
Next
MODEL
31-gemmascope-2-res-16k
Source/SAE
INDEX
Go
Explanations
bad, evil, harmful concepts
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
The neuron responds to occurrences of the adjective “bad,” flagging that specific negative descriptor.
oai_token-act-pair · o4-mini
Triggered by @jyhe0408
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
How To Load
Prompts (Dashboard)
392,802 prompts, 256 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
No Configuration Found
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gemma-3-12b/31-gemmascope-2-res-16k/1778?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-3-12b/31-gemmascope-2-res-16k/1778?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
挲
0.65
enrich
0.63
izzata
0.60
Alka
0.59
恬
0.57
Sousa
0.56
טה
0.56
enriching
0.56
ıza
0.55
खुश
0.55
POSITIVE LOGITS
Bad
1.29
bad
1.27
bad
1.22
Bad
1.21
坏
1.20
BAD
1.15
壞
1.08
BAD
1.06
mauvaise
0.90
badly
0.89
Act
ivations
Density 0.294%
Test
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
