© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32747
    Prev
    Next
    INDEX
    Explanations

    Sheriff's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    </h4>
    -1.91
    哂
    -1.77
     gewähr
    -1.73
    </em>
    -1.67
     dreary
    -1.66
    eficent
    -1.61
     fraught
    -1.60
    那麼
    -1.59
     horrendous
    -1.59
    +```
    -1.57
    POSITIVE LOGITS
    錒
    1.92
    ↵
    1.71
    ’，
    1.69
     ū
    1.66
     unu
    1.66
    ſtra
    1.62
     itſelf
    1.61
     sene
    1.60
    ver
    1.58
     ?
    1.57
    Activations Density 0.015%

    No Known Activations