© 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. 90443
    Prev
    Next
    INDEX
    Explanations

    materials coated

    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
    1
    -2.06
    le
    -2.03
    {
    -1.98
    /
    -1.95
     to
    -1.95
     الحدود
    -1.91
     Sumber
    -1.90
    "
    -1.77
    ID
    -1.73
     höher
    -1.73
    POSITIVE LOGITS
    colgante
    2.48
    鱨
    2.38
    ៚
    2.22
    龃
    2.16
    pulseira
    2.16
    CurtirCurtir
    2.16
    錵
    2.14
    不论
    2.13
     acusa
    2.09
     Organisator
    2.06
    Activations Density 0.011%

    No Known Activations