© 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. 68369
    Prev
    Next
    INDEX
    Explanations

    Maxim and related names

    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
     whoſe
    -2.77
    佉
    -2.66
     Zuhause
    -2.66
    "",
    -2.59
    stil
    -2.58
    杁
    -2.56
    gucig
    -2.52
    "$_
    -2.50
    湏
    -2.50
     accents
    -2.48
    POSITIVE LOGITS
    the
    4.63
    n
    3.08
     و
    2.88
    m
    2.83
     и
    2.83
    ate
    2.70
    as
    2.67
    You
    2.66
     وأ
    2.63
     وع
    2.59
    Activations Density 0.003%

    No Known Activations