© 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. 3444
    Prev
    Next
    INDEX
    Explanations

    data bytes

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

    The neuron fires on the literal token “bytes,” especially in code import or package‐reference contexts.

    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
    یت
    -0.98
    IS
    -0.84
     paciencia
    -0.84
    inematics
    -0.83
     versuchen
    -0.83
    一定会
    -0.82
    アーム
    -0.82
     Skeletal
    -0.82
    绘画
    -0.81
     rivales
    -0.81
    POSITIVE LOGITS
    ENCODING
    0.98
     ")");
    0.95
     مشارکت‌کنندگان
    0.93
     Between
    0.90
    月末
    0.88
    XIII
    0.84
     }?>
    0.83
    
    0.81
    轶
    0.80
    avro
    0.79
    Activations Density 0.003%

    No Known Activations