© 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. 113902
    Prev
    Next
    INDEX
    Explanations

    "Quad" followed by specific compounds

    np_acts-logits-general · gemini-2.5-flash-lite

    words beginning with "Quad" or variants of quadrilateral/quadruple terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on the substring “quad” (i.e. tokens or words beginning with “quad”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     แต่
    -2.77
    鷥
    -2.75
    乆
    -2.63
    更好
    -2.61
    ⁛
    -2.59
     aña
    -2.58
     But
    -2.53
    pecabe
    -2.48
    "$_
    -2.44
    盌
    -2.44
    POSITIVE LOGITS
    ’
    3.41
    進入
    2.92
    In
    2.84
    ',
    2.56
    ном
    2.52
    ！】
    2.45
    \
    2.45
    有點
    2.44
    尋找
    2.36
     expérimentés
    2.34
    Activations Density 0.008%

    No Known Activations