© 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. 10-GEMMASCOPE-RES-131K
    7. 104019
    Prev
    Next
    INDEX
    Explanations

    jackpot handpay

    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_10/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
    躥
    -2.50
    ⸰
    -2.47
     insectes
    -2.45
    拊
    -2.45
     شیپور
    -2.45
    麈
    -2.44
    лением
    -2.36
    缡
    -2.25
    ;
    -2.23
     フレア
    -2.23
    POSITIVE LOGITS
     Если
    2.20
    Both
    2.20
     According
    2.19
    Several
    2.16
    From
    2.14
     Both
    2.13
     
    2.11
    当然是
    2.11
    Another
    2.06
    最初の
    2.06
    Activations Density 0.002%

    No Known Activations