© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20970
    Prev
    Next
    INDEX
    Explanations

    following specified, other payment, Q: questions, Appellee

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     probablement
    -1.97
     krak
    -1.88
     quelquefois
    -1.77
     koe
    -1.73
     ginge
    -1.68
     οὐ
    -1.66
     heng
    -1.65
     ſol
    -1.63
     Eſ
    -1.63
    probably
    -1.61
    POSITIVE LOGITS
     or
    3.09
     in
    2.09
     without
    1.91
     with
    1.91
     on
    1.82
     any
    1.80
     perawatan
    1.79
     السياس
    1.78
     provide
    1.77
     before
    1.75
    Activations Density 0.031%

    No Known Activations