© 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
GEMMA-3-27B-IT · 40-GEMMASCOPE-2-RES-262K · 35966 ｜ Neuronpedia
Home
Gemma-3-27B-IT
40-GEMMASCOPE-2-RES-262K
35966
Prev
Next
MODEL
40-gemmascope-2-res-262k
Source/SAE
INDEX
Go
Explanations
one followed by modals or nouns
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-2-27b-it/resid_post/layer_40_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/40-gemmascope-2-res-262k/35966?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/40-gemmascope-2-res-262k/35966?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
één
0.46
دیگه
0.46
นึง
0.45
trz
0.45
nifty
0.44
ુપ
0.43
onimo
0.43
ኙ
0.43
ెం
0.42
yksi
0.42
POSITIVE LOGITS
一系列
0.44
who
0.42
系列
0.40
whose
0.39
series
0.39
who
0.39
सो
0.39
whose
0.39
voc
0.38
rump
0.38
Act
ivations
Density 0.003%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
