© 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. 129515
    Prev
    Next
    INDEX
    Explanations

    material, Basel, French, Conservatives

    np_acts-logits-general · gemini-2.5-flash-lite

    Would You Rather choices

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Jays
    0.47
     perempt
    0.47
     برابر
    0.45
    ва
    0.45
     けれど
    0.44
    練
    0.44
    вах
    0.42
    دام
    0.41
     AUTHOR
    0.41
     bào
    0.41
    POSITIVE LOGITS
    с
    0.48
    pm
    0.47
    }:\
    0.47
     JsonSerializer
    0.46
    idet
    0.43
     ചെയ്യുന്നത്
    0.43
    TotalPrice
    0.43
    QRCode
    0.42
    ides
    0.42
    gm
    0.42
    Activations Density 0.000%

    No Known Activations