© 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. 10-GEMMASCOPE-RES-131K
    7. 98777
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and indices

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

    The neuron activates on numeric expressions—literal numbers, subscripts, and other math‐mode numerals—within the text.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     wyposaż
    -1.79
    '
    -1.70
     their
    -1.53
     pretože
    -1.52
    がありました
    -1.51
     väč
    -1.51
     hectáreas
    -1.48
     last
    -1.48
     key
    -1.47
     pictureBox
    -1.46
    POSITIVE LOGITS
     Auffassung
    1.67
    ARANCE
    1.67
     évêque
    1.67
     esempi
    1.63
    CORO
    1.61
    вне
    1.61
     episodi
    1.60
    versies
    1.59
    Ǎ
    1.57
    Its
    1.56
    Activations Density 0.002%

    No Known Activations