© 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. 47373
    Prev
    Next
    INDEX
    Explanations

    programming and mathematical function definitions

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

    The neuron is triggered by numeric tokens (sequences of digits) 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_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
    ائ
    -0.83
     tự
    -0.75
     galloping
    -0.73
    UTF
    -0.71
     помо
    -0.68
    Tomas
    -0.68
     Tomas
    -0.67
    ×
    -0.66
     Toxicol
    -0.65
    Five
    -0.64
    POSITIVE LOGITS
     foil
    0.68
    ㅋㅋ
    0.66
     snail
    0.65
     tivi
    0.65
     có
    0.65
    erencia
    0.63
    卡片
    0.63
     cikk
    0.63
     eneste
    0.63
     داخل
    0.63
    Activations Density 0.357%

    No Known Activations