© 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. 124126
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ᠁
    -1.42
     kablo
    -1.33
    MENAFN
    -1.32
    Estar
    -1.32
    bege
    -1.32
     parachoque
    -1.31
     nya
    -1.30
    潆
    -1.30
    Eres
    -1.27
    Tages
    -1.27
    POSITIVE LOGITS
    "
    1.97
    $
    1.56
    In
    1.40
    ’
    1.36
    1
    1.34
    A
    1.33
    s
    1.31
    [
    1.30
    ?
    1.29
    `
    1.28
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.