© 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. 34-GEMMASCOPE-RES-131K
    4. 83191
    Prev
    Next
    INDEX
    Explanations

    calendar

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

    The neuron strongly activates on numeric tokens and separators when they appear as part of dates or times (e.g. “Date … today with 0:0:0”), so it is detecting numeric date/time expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    programming code related to date and calendar operations.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of programming/date-time handling, especially code and APIs for dates, calendars, and scheduling in languages and frameworks.

    oai_token-act-pair · gpt-5Triggered 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
    Neste
    -0.89
    你了
    -0.85
    żesz
    -0.79
    Đặc
    -0.75
    olisian
    -0.75
     delaying
    -0.73
     probar
    -0.73
    yski
    -0.73
     Neste
    -0.71
     NASH
    -0.70
    POSITIVE LOGITS
     calendar
    2.67
     Calendar
    2.53
    Calendar
    2.53
    calendar
    2.23
     calendars
    2.16
    CALENDAR
    1.64
     CALENDAR
    1.61
     cal
    1.56
     kalender
    1.52
     Greg
    1.52
    Activations Density 0.020%

    No Known Activations