© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 29018
    Prev
    Next
    INDEX
    Explanations

    dates and events

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

    This neuron specifically detects the period in month abbreviations (e.g. the “.” in “Nov.”, “Oct.”, etc.) as part of date references.

    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
    ⎔
    -2.39
    ?
    -2.25
     ทั้ง
    -2.14
    त
    -2.11
    閙
    -2.06
     conférences
    -2.03
    т
    -1.97
     effectué
    -1.95
    ا
    -1.94
    .........
    -1.93
    POSITIVE LOGITS
     or
    3.13
     and
    2.59
     as
    2.53
     for
    2.23
     інші
    2.19
     with
    2.11
     at
    2.06
     flesta
    1.98
     even
    1.95
     that
    1.89
    Activations Density 0.017%

    No Known Activations