© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Community
Blog
Privacy & Terms
Contact
Sign In
Home
Gemma-3-12B-IT
12-GEMMASCOPE-2-RES-262K
5965
Prev
Next
MODEL
12-gemmascope-2-res-262k
Source/SAE
INDEX
Go
Explanations
story want character development leak stolen data video elements science
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Configuration
google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
How To Load
Prompts (Dashboard)
238,145 prompts, 512 tokens each
Dataset (Dashboard)
lmsys + oasst1
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-it/12-gemmascope-2-res-262k/5965?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-it/12-gemmascope-2-res-262k/5965?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
which
1.02
an
1.01
the
0.94
а
0.93
oscill
0.93
котором
0.93
РА
0.91
sebuah
0.90
деву
0.90
and
0.89
POSITIVE LOGITS
↵↵
1.46
am
1.34
ou
1.19
ak
1.19
↵
1.18
om
1.18
ot
1.13
ur
1.09
ai
1.08
al
1.05
Act
ivations
Density 4.903%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
