© 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. 57657
    Prev
    Next
    INDEX
    Explanations

    animals in lists

    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
    lacement
    -0.91
    ↵↵↵
    -0.89
    ensión
    -0.77
     whose
    -0.76
     Abschnitt
    -0.73
    ragment
    -0.73
     Dunne
    -0.71
    THEOREM
    -0.71
    Пото
    -0.71
    eger
    -0.71
    POSITIVE LOGITS
    Pj
    0.79
    stealth
    0.77
    inginan
    0.73
     sangue
    0.73
     fervent
    0.72
    ^*
    0.71
     المع
    0.70
    デア
    0.70
    *
    0.69
     Galleries
    0.68
    Activations Density 0.019%

    No Known Activations