© 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. 22-GEMMASCOPE-RES-131K
    7. 39580
    Prev
    Next
    INDEX
    Explanations

    specific column in spreadsheet row

    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_22/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
    ioon
    -0.86
    кому
    -0.80
     тени
    -0.79
     искать
    -0.77
     Verme
    -0.75
     activates
    -0.75
     meses
    -0.72
    shub
    -0.72
    ный
    -0.71
     температуре
    -0.71
    POSITIVE LOGITS
    !
    0.79
     пресс
    0.77
    Printed
    0.76
     algebraic
    0.75
     européens
    0.73
    ⣄
    0.73
    يطاليا
    0.72
     ہو
    0.71
    espero
    0.71
    [{{
    0.71
    Activations Density 0.103%

    No Known Activations