© 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. 67119
    Prev
    Next
    INDEX
    Explanations

    subject to change or terms

    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
    小花
    -1.85
    fatti
    -1.73
    欒
    -1.72
    tabilidade
    -1.68
     corda
    -1.68
     have
    -1.64
    ullable
    -1.63
    izarra
    -1.62
    ностях
    -1.62
    glers
    -1.61
    POSITIVE LOGITS
    indicates
    1.92
    produces
    1.89
    趼
    1.87
     Eigentü
    1.84
    菝
    1.80
    ݯ
    1.78
    provides
    1.73
    ݮ
    1.72
    al
    1.70
     area
    1.67
    Activations Density 0.017%

    No Known Activations