© 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. 22-GEMMASCOPE-RES-131K
    7. 32576
    Prev
    Next
    INDEX
    Explanations

    foreign language text

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

    The neuron activates on numeric tokens that include a decimal point (i.e. floating‐point numbers).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     only
    -1.59
     on
    -1.56
     in
    -1.53
     at
    -1.48
     to
    -1.47
     for
    -1.34
     as
    -1.28
     just
    -1.27
     one
    -1.27
     (
    -1.26
    POSITIVE LOGITS
     aceasta
    1.68
     soddis
    1.54
     rispar
    1.52
     této
    1.44
     angeboten
    1.43
    Sonntag
    1.40
    Deel
    1.36
     taşlı
    1.35
    Etape
    1.35
     risol
    1.34
    Activations Density 0.000%

    No Known Activations