© 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-3-27B-IT
16-GEMMASCOPE-2-RES-262K
35482
Prev
Next
MODEL
16-gemmascope-2-res-262k
Source/SAE
INDEX
Go
Explanations
cop, copilot, killer, donor
np_acts-logits-general · gemini-2.5-flash-lite
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Interpretable Score
Intrusion Detection
Top Features by Cosine Similarity
Configuration
google/gemma-scope-2-27b-it/resid_post/layer_16_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-3-27b-it/16-gemmascope-2-res-262k/35482?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-3-27b-it/16-gemmascope-2-res-262k/35482?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
ت
1.17
ين
1.07
т
1.01
تي
0.96
ajout
0.94
ע
0.94
ти
0.93
autoComplete
0.91
ع
0.90
ко
0.89
POSITIVE LOGITS
to
1.57
1
1.39
that
1.24
که
1.13
that
1.09
of
1.04
'
0.99
5
0.99
</h2>
0.98
6
0.96
Act
ivations
Density 0.003%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
