© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50147
    Prev
    Next
    INDEX
    Explanations

    variables and formulas

    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
     rea
    -0.75
    льности
    -0.74
    Sofia
    -0.73
    лла
    -0.73
    阴影
    -0.70
     Übers
    -0.70
    鍊
    -0.69
    Flare
    -0.69
    Chara
    -0.68
    CDD
    -0.66
    POSITIVE LOGITS
    "]))
    0.83
    ㈢
    0.73
    glied
    0.73
    ILI
    0.72
     Blum
    0.72
    supposed
    0.71
    不错
    0.71
     faute
    0.71
    reuth
    0.71
    нець
    0.70
    Activations Density 0.031%

    No Known Activations