© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86603
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and symbols

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

    The neuron fires on tokens that are multi-digit numerals (integer sequences) appearing inside braces in math expressions.

    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
    ;
    -2.53
     uren
    -2.34
    ’,
    -2.33
    ’.
    -2.31
     ideen
    -2.28
    𓋼
    -2.23
    ’-
    -2.20
    atecas
    -2.19
    ,’
    -2.16
     italie
    -2.14
    POSITIVE LOGITS
     '
    3.52
     was
    3.06
    ar
    2.69
     shines
    2.52
    d
    2.42
     {
    2.41
     )
    2.41
     "
    2.34
    j
    2.30
     sogen
    2.22
    Activations Density 0.007%

    No Known Activations