© 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. 10988
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     jú
    -1.48
    tembro
    -1.43
     japones
    -1.41
    Zubereitung
    -1.38
    vább
    -1.37
     sezonu
    -1.37
     gången
    -1.34
     __
    -1.33
     Diretto
    -1.32
    atischen
    -1.32
    POSITIVE LOGITS
    [
    1.54
    {
    1.52
    ~
    1.52
    ar
    1.41
    <strong>
    1.38
    <
    1.38
    o
    1.37
    u
    1.37
    <em>
    1.36
    es
    1.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.