© 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. 22-GEMMASCOPE-RES-131K
    7. 127728
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on “return” statements that return a hard‐coded numeric literal.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    code returning results

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     acestui
    -1.02
    ṓ
    -0.96
    긍
    -0.93
     nonatomic
    -0.92
    ということは
    -0.90
    ᾿
    -0.89
    形势
    -0.89
    geſ
    -0.88
    等人
    -0.88
    ངས་
    -0.88
    POSITIVE LOGITS
    QRect
    1.02
     of
    1.02
    boss
    0.95
    Coeff
    0.94
    XPATH
    0.91
     east
    0.90
     Youtube
    0.89
    "}";
    0.89
    animity
    0.89
    "");
    0.88
    Activations Density 0.003%

    No Known Activations