© 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. 34-GEMMASCOPE-RES-131K
    7. 78857
    Prev
    Next
    INDEX
    Explanations

    American football teams

    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_34/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
    camp
    -0.72
    CAMP
    -0.71
     Syr
    -0.66
     descripción
    -0.65
     ensembles
    -0.65
     Tram
    -0.64
     Stamp
    -0.63
     Brava
    -0.63
    dc
    -0.63
    ئة
    -0.62
    POSITIVE LOGITS
    范
    0.68
     بروز
    0.65
     coercive
    0.65
    setzt
    0.65
    \,.
    0.63
     quadrat
    0.63
     ADMINISTR
    0.62
     princesas
    0.62
     вход
    0.62
     čes
    0.62
    Activations Density 0.088%

    No Known Activations