© 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. 83806
    Prev
    Next
    INDEX
    Explanations

    adverbs of frequency or time

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

    The neuron specifically fires on numeric tokens showing fractional or decimal values (e.g. 120.5, 24.875, 12.625).

    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
     when
    -1.63
     penyanyi
    -1.56
    Opere
    -1.54
    蒾
    -1.52
    Mereka
    -1.44
     pemuda
    -1.38
     Sebuah
    -1.36
     with
    -1.36
    Formazione
    -1.35
    每个
    -1.34
    POSITIVE LOGITS
     welchen
    1.55
     examples
    1.49
     altamente
    1.48
     diversos
    1.45
     andern
    1.44
    .
    1.41
     agujeros
    1.41
    も見
    1.38
     enters
    1.36
     significativo
    1.36
    Activations Density 0.170%

    No Known Activations