© 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. 34-GEMMASCOPE-RES-131K
    7. 3572
    Prev
    Next
    INDEX
    Explanations

    code string join operation

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

    The neuron primarily lights up on numeric literals (e.g. tokens consisting of digits) in code.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    </
    -0.79
     ));
    -0.76
    ///<
    -0.76
    <h3>
    -0.76
    hale
    -0.75
    ждается
    -0.75
    urés
    -0.74
    леп
    -0.73
     prek
    -0.73
    互联网档案馆
    -0.72
    POSITIVE LOGITS
    ineries
    0.77
     nonetheless
    0.75
     だけ
    0.73
     there
    0.71
     provoking
    0.71
     NotFound
    0.69
    ッズ
    0.68
    IEDAD
    0.68
    tious
    0.68
    fbe
    0.67
    Activations Density 0.024%

    No Known Activations