© 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. 57339
    Prev
    Next
    INDEX
    Explanations

    file path and metadata

    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
     textual
    -0.69
     governing
    -0.65
     חיצוניים
    -0.65
    jęt
    -0.62
     culminating
    -0.62
    事業
    -0.61
     Streak
    -0.61
     symbolic
    -0.61
    "",
    -0.61
     Simpli
    -0.61
    POSITIVE LOGITS
    sediaan
    0.69
    Saver
    0.68
    messer
    0.67
     LHS
    0.67
    ('../../../
    0.66
    ями
    0.66
    Kristen
    0.65
     variar
    0.65
    rón
    0.65
    REAT
    0.64
    Activations Density 0.062%

    No Known Activations