© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 179970
    Prev
    Next
    INDEX
    Explanations

    crime and fiction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    🌞
    0.52
     pozwala
    0.50
     spans
    0.48
     allows
    0.46
    ဟုတ်
    0.46
     অনুভূত
    0.46
    Ľ
    0.45
     Span
    0.45
     vyroben
    0.45
    span
    0.45
    POSITIVE LOGITS
    વતી
    0.47
    хбет
    0.43
    礼
    0.43
    ită
    0.43
     पौधा
    0.43
    ki
    0.42
    itum
    0.41
    гова
    0.41
    uva
    0.41
    мести
    0.41
    Activations Density 0.000%

    No Known Activations