© 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. 1805
    Prev
    Next
    INDEX
    Explanations

    dates and fractions

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

    This neuron detects forward‐slash characters ("/") in the text, as used in dates, fractions, and similar expressions.

    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
     fün
    -1.49
     a
    -1.36
    ’
    -1.34
    another
    -1.32
     το
    -1.32
     น
    -1.28
     senderismo
    -1.27
    <
    -1.24
     esquí
    -1.21
    ‘
    -1.20
    POSITIVE LOGITS
     establishing
    1.27
     осіб
    1.23
     zile
    1.21
    suc
    1.20
    ้อน
    1.19
     vidare
    1.19
     Baskets
    1.18
     意思
    1.16
    tação
    1.16
    cembre
    1.16
    Activations Density 0.027%

    No Known Activations