© 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. 32727
    Prev
    Next
    INDEX
    Explanations

    commands and code blocks

    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
    зії
    -0.96
     on
    -0.96
     darbu
    -0.87
    itarianism
    -0.86
     Note
    -0.85
    نکته
    -0.85
     an
    -0.84
     Verg
    -0.84
     Altstadt
    -0.83
    нение
    -0.81
    POSITIVE LOGITS
     asamblea
    0.95
     ваших
    0.88
    例えば
    0.84
     вашу
    0.84
    ͫ
    0.83
    や
    0.81
     র
    0.81
     pegatina
    0.79
     correos
    0.79
    🕗
    0.79
    Activations Density 0.007%

    No Known Activations