© 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. 41176
    Prev
    Next
    INDEX
    Explanations

    lists of numbers and words

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

    This neuron detects numeric sports statistics, such as play yardage, point totals, inning counts, and other game-related numbers.

    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
     THEIR
    -1.65
     épu
    -1.58
    según
    -1.55
    PÁG
    -1.55
    他们的
    -1.55
     Algunos
    -1.54
     jejich
    -1.54
    姈
    -1.53
     accél
    -1.52
    their
    -1.51
    POSITIVE LOGITS
     two
    1.76
     another
    1.72
     in
    1.66
     the
    1.66
     during
    1.62
     all
    1.61
     gave
    1.61
     before
    1.59
     helped
    1.54
     then
    1.48
    Activations Density 0.041%

    No Known Activations