© 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. 22762
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming syntax

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

    The neuron fires on numeric tokens (i.e. literal numbers) in 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
    \
    -2.33
    </h3>
    -2.03
     \\
    -1.71
    if
    -1.70
    .
    -1.67
    _
    -1.66
    //
    -1.62
    <h3>
    -1.58
     is
    -1.52
    нет
    -1.50
    POSITIVE LOGITS
     cerveau
    1.80
     anillos
    1.51
     travailleurs
    1.45
     lâmpada
    1.45
    tienen
    1.43
    遢
    1.41
     paisajes
    1.39
     séjours
    1.38
     cielos
    1.37
     acteurs
    1.36
    Activations Density 0.020%

    No Known Activations