© 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. 40200
    Prev
    Next
    INDEX
    Explanations

    type, path, order, files, version

    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
     on
    -2.77
     or
    -2.64
     this
    -2.61
     without
    -2.47
     there
    -2.39
     in
    -2.39
     of
    -2.25
    0
    -2.25
     at
    -2.09
     before
    -2.09
    POSITIVE LOGITS
    erobic
    2.86
    odyne
    2.47
    蚰
    2.38
     rése
    2.25
    镲
    2.16
    Kde
    2.14
    錾
    2.14
     花纹
    2.14
    秾
    2.06
    罍
    2.06
    Activations Density 0.148%

    No Known Activations