© 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. 57733
    Prev
    Next
    INDEX
    Explanations

    performance metrics and resource limits

    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
    学位
    -0.71
     tokenId
    -0.71
     conftest
    -0.71
     tỏ
    -0.71
    fantasia
    -0.71
    urna
    -0.70
    cię
    -0.66
     eredeti
    -0.65
     духов
    -0.64
     motivational
    -0.64
    POSITIVE LOGITS
     dominant
    0.91
    Peak
    0.88
    llano
    0.86
     peak
    0.85
    peak
    0.79
     Peak
    0.77
     QtWidgets
    0.77
    Brighton
    0.77
    getBytes
    0.76
     변
    0.76
    Activations Density 0.033%

    No Known Activations