© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 3886
    Prev
    Next
    INDEX
    Explanations

    calendar units

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

    The neuron detects numeric tokens representing quantities or statistics (e.g., counts, measurements, scores).

    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
     policías
    -1.70
    ¹)
    -1.68
    はこの
    -1.66
     metrów
    -1.61
    閪
    -1.56
     akhirnya
    -1.54
     zove
    -1.52
     membutuhkan
    -1.50
     botões
    -1.50
     canais
    -1.48
    POSITIVE LOGITS
     The
    1.73
    st
    1.63
    and
    1.61
     [
    1.60
    .
    1.55
    not
    1.48
     not
    1.46
     our
    1.45
    or
    1.44
    the
    1.43
    Activations Density 0.009%

    No Known Activations