Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Gemma-3-4B-IT
17-GEMMASCOPE-2-RES-65K
47131
Prev
Next
MODEL
17-gemmascope-2-res-65k
Source/SAE
INDEX
Go
Explanations
algorithmic techniques, bias, thinking
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-2-4b-it/resid_post/layer_17_width_65k_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-3-4b-it/17-gemmascope-2-res-65k/47131?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-3-4b-it/17-gemmascope-2-res-65k/47131?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
ことになる
1.52
u
1.46
ificate
1.45
homologs
1.36
||
1.36
া
1.33
ા
1.31
keys
1.30
नों
1.29
sehen
1.28
POSITIVE LOGITS
िक
1.90
pwm
1.89
𝐲
1.84
𝐡
1.80
𝐞
1.79
də
1.75
дә
1.72
д
1.69
dagen
1.68
𝗚
1.68
Act
ivations
Density 0.001%
Test
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
