© 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. 14861
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    This neuron detects numeric tokens or sequences (including dates, times, and other multi‐digit 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
    Pgina
    -1.66
    CORO
    -1.47
    (ﾟ
    -1.45
    𖣘
    -1.45
    (*^^
    -1.45
    obrázek
    -1.43
     beeind
    -1.41
    waniem
    -1.40
     beweisen
    -1.38
     beziehungs
    -1.38
    POSITIVE LOGITS
    跸
    1.73
    '
    1.63
    鸱
    1.59
    .
    1.54
    focused
    1.46
    菝
    1.45
     '_'
    1.41
     comprando
    1.39
     abbreviated
    1.35
     on
    1.34
    Activations Density 0.065%

    No Known Activations