© 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. 22-GEMMASCOPE-RES-131K
    7. 72514
    Prev
    Next
    INDEX
    Explanations

    numbers and arithmetic operations

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

    The neuron activates on numeric tokens—especially digits in decimal numbers—i.e. parts of numeric constants in equations or measurements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ⎔
    -1.78
    圌
    -1.75
    
    -1.64
    邶
    -1.62
    ᯾
    -1.59
     dreadful
    -1.58
    旄
    -1.57
    拊
    -1.55
     raiſ
    -1.55
    罴
    -1.55
    POSITIVE LOGITS
     in
    1.77
     from
    1.73
     EVERY
    1.67
    just
    1.61
     when
    1.61
     because
    1.61
    !
    1.55
    、
    1.55
     Every
    1.55
     можуть
    1.45
    Activations Density 0.015%

    No Known Activations