© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38610
    Prev
    Next
    INDEX
    Explanations

    intelligence quotient

    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
    ↵
    -3.06
     longtime
    -2.53
    jenigen
    -2.41
     ,
    -2.36
    It
    -2.34
     Not
    -2.31
    鄲
    -2.27
     –
    -2.25
    MLLoader
    -2.23
    IBILITIES
    -2.23
    POSITIVE LOGITS
    .
    3.44
    ’
    3.14
    z
    2.47
    {
    2.42
     prepares
    2.39
    삵
    2.31
    ian
    2.23
     defines
    2.19
     avoids
    2.17
     asks
    2.14
    Activations Density 0.002%

    No Known Activations