© 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. 34-GEMMASCOPE-RES-131K
    7. 23920
    Prev
    Next
    INDEX
    Explanations

    calendar and events

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

    The neuron fires on references to calendar‐event creation, in particular on ICS/vCalendar keywords (e.g. “BEGIN:”, “VEVENT”, “END:”), “calendar,” “event,” “using,” and other tokens related to generating calendar events.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     specials
    -0.69
     dosa
    -0.68
    ław
    -0.68
     Gothic
    -0.65
     headquarters
    -0.65
     tē
    -0.65
     sklep
    -0.63
    mojo
    -0.63
    ねー
    -0.63
     medieval
    -0.63
    POSITIVE LOGITS
     calendar
    3.31
     Calendar
    2.64
    calendar
    2.63
     calendars
    2.61
    Calendar
    2.56
     кален
    2.16
     calend
    2.06
     CALENDAR
    2.06
    CALENDAR
    1.95
     Calend
    1.77
    Activations Density 0.084%

    No Known Activations