© 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. 1850
    Prev
    Next
    INDEX
    Explanations

    numbers and names

    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
    介紹
    -0.79
    Ryu
    -0.78
    が含ま
    -0.77
     atv
    -0.71
     オフ
    -0.71
    分为
    -0.70
     Miscell
    -0.70
     発表
    -0.69
    blob
    -0.68
     которых
    -0.68
    POSITIVE LOGITS
     Francisco
    0.87
    ・・・
    0.82
     servent
    0.79
    uride
    0.77
     Quickly
    0.77
    ментов
    0.76
    getMessage
    0.76
    骛
    0.76
    RowIndex
    0.76
     viel
    0.75
    Activations Density 0.001%

    No Known Activations