© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14122
    Prev
    Next
    INDEX
    Explanations

    league and division names

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

    The neuron’s primary function is to detect numeric data (quantities, league levels, scores, years, etc.) in the text.

    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
     protože
    -1.84
    我也不
    -1.62
    扨
    -1.53
     dnes
    -1.48
     trám
    -1.47
     produkty
    -1.46
    bindet
    -1.43
     sorpresas
    -1.42
    唻
    -1.39
     estancias
    -1.38
    POSITIVE LOGITS
     of
    2.33
    '
    1.34
    er
    1.30
     eleven
    1.25
     has
    1.24
     all
    1.23
     well
    1.21
     under
    1.20
     not
    1.17
    濕
    1.17
    Activations Density 0.110%

    No Known Activations