© 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. 48504
    Prev
    Next
    INDEX
    Explanations

    free of charge

    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
     Start
    -0.77
    حاب
    -0.77
     start
    -0.75
     начинается
    -0.74
     starts
    -0.74
    生素
    -0.73
    RESUMO
    -0.72
    imageUrl
    -0.71
     शुरू
    -0.71
     институт
    -0.70
    POSITIVE LOGITS
     樹
    0.75
    tern
    0.74
    plz
    0.72
    標準
    0.71
    红了
    0.70
     Nodo
    0.70
     trenes
    0.70
     отредакти
    0.69
    geth
    0.69
     Paging
    0.69
    Activations Density 0.023%

    No Known Activations