© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73357
    Prev
    Next
    INDEX
    Explanations

    itemsbeveragesappliancesproteinsbooksvehiclecharactersinformationequipmentvalueaddress

    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
    >",
    
    -1.26
    Сю
    -1.22
    ۰۱
    -1.18
     bereits
    -1.15
    isait
    -1.13
     ۴
    -1.13
     four
    -1.12
    ohne
    -1.12
    \|^{
    -1.11
    正当
    -1.11
    POSITIVE LOGITS
     that
    2.98
     you
    2.33
     we
    1.52
    ที่
    1.50
     chosen
    1.45
     που
    1.45
     الذي
    1.43
     of
    1.38
     التي
    1.38
     requested
    1.30
    Activations Density 0.078%

    No Known Activations