© 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. 63256
    Prev
    Next
    INDEX
    Explanations

    Q: A: case Payroll: clone avoid

    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
    🎰
    -0.86
     cabra
    -0.76
    euvres
    -0.74
    ラグ
    -0.73
    lês
    -0.73
    feest
    -0.72
    ocyto
    -0.72
     Lucifer
    -0.71
    irrit
    -0.71
    お待ちしております
    -0.71
    POSITIVE LOGITS
    newArrayList
    0.84
    déric
    0.79
    gfx
    0.77
     ву
    0.76
     orthogonal
    0.75
    acio
    0.75
     mxArray
    0.75
    ępnie
    0.74
     possui
    0.74
    Ќ
    0.74
    Activations Density 0.002%

    No Known Activations