© 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. 6702
    Prev
    Next
    INDEX
    Explanations

    swing in golf, music, politics, or Java

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

    The neuron responds specifically to occurrences of the word “swing.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    缫
    -2.77
    呖
    -2.70
    0
    -2.67
    ⸫
    -2.64
    "}}>
    -2.45
    珢
    -2.45
    ”
    -2.39
    軚
    -2.31
    </i>
    -2.30
    “
    -2.28
    POSITIVE LOGITS
    $,
    2.53
    y
    2.33
     pernicious
    2.19
    
    2.13
    ).
    2.13
     selben
    2.11
    ;
    2.11
    澌
    2.08
    ೢ
    2.05
    ису
    2.03
    Activations Density 0.003%

    No Known Activations