© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58339
    Prev
    Next
    INDEX
    Explanations

    Python range and loops

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

    The neuron fires on numeric constants (digits) in code, especially the numeric arguments passed to functions like range() or randint().

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     ブログ
    -1.13
    ];
    -1.04
    儼
    -0.97
     것은
    -0.96
     (!__
    -0.95
    معرفی
    -0.94
    );
    -0.94
    jooq
    -0.94
    )][
    -0.93
     ベン
    -0.93
    POSITIVE LOGITS
    (
    1.03
     start
    1.02
    ():
    0.95
     (
    0.94
    гай
    0.90
    各样的
    0.86
    烘
    0.85
     virtuelle
    0.84
    究
    0.82
    kud
    0.82
    Activations Density 0.003%

    No Known Activations