© 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. 10-GEMMASCOPE-RES-131K
    7. 72608
    Prev
    Next
    INDEX
    Explanations

    math problems and code structures

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

    This neuron activates on numeric tokens—especially decimal numbers—in the text.

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

    No Comments

    Negative Logits
    ⦊
    -1.92
     新聞
    -1.81
    During
    -1.81
     Both
    -1.77
    結果は
    -1.74
    8
    -1.74
    ()");
    -1.69
    This
    -1.69
    akterysty
    -1.66
    犭
    -1.66
    POSITIVE LOGITS
    ’
    2.05
     Перейти
    1.81
     '
    1.77
     quintessential
    1.73
     históricas
    1.73
     большин
    1.72
    '
    1.72
     strukt
    1.71
     feine
    1.70
    ”
    1.70
    Activations Density 0.004%

    No Known Activations