© 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. 104738
    Prev
    Next
    INDEX
    Explanations

    scoring victory

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

    The neuron specializes in picking out numeric tokens—especially sports scores and statistical figures (e.g. “3-2,” “39.5,” “58.75”)—in game reports.

    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
     like
    -1.72
    Recently
    -1.70
     berbagai
    -1.56
    However
    -1.45
     Therefore
    -1.42
     is
    -1.36
     beberapa
    -1.35
     recientemente
    -1.35
     it
    -1.34
     such
    -1.31
    POSITIVE LOGITS
    ($__
    1.27
     setAddress
    1.25
    plains
    1.25
    ଼
    1.24
     осу
    1.23
    ési
    1.20
    ⅖
    1.20
    iciaries
    1.20
    []{"
    1.20
    当时
    1.20
    Activations Density 0.064%

    No Known Activations