© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 54275
    Prev
    Next
    INDEX
    Explanations

    extra

    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
    iddhar
    -0.77
    诡
    -0.75
     compromises
    -0.75
    ĩ
    -0.73
     ytter
    -0.73
    stock
    -0.73
     investigating
    -0.71
    緝
    -0.71
     prz
    -0.70
    strijd
    -0.70
    POSITIVE LOGITS
    textra
    1.09
    arate
    0.77
     extra
    0.74
     zusätz
    0.74
    незон
    0.73
     competitively
    0.73
     EXTR
    0.72
    Extra
    0.72
     ブラウン
    0.72
    extra
    0.71
    Activations Density 0.033%

    No Known Activations