© 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. 15786
    Prev
    Next
    INDEX
    Explanations

    numbers following 'a total of'

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

    The neuron responds to numeric tokens (counts, measurements, and decimal values) 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
     as
    -1.55
     on
    -1.45
    [
    -1.38
     one
    -1.31
     \
    -1.30
     /
    -1.28
     [
    -1.23
     h
    -1.23
    <tr>
    -1.23
     For
    -1.21
    POSITIVE LOGITS
     olika
    1.62
    訁
    1.58
    tront
    1.57
     decidi
    1.54
     många
    1.52
    including
    1.47
     故
    1.46
    hoes
    1.46
    璈
    1.46
    姽
    1.43
    Activations Density 0.054%

    No Known Activations