© 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. 81458
    Prev
    Next
    INDEX
    Explanations

    java.util.Calendar instances

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

    The neuron fires on Java time/calendar API class names (e.g. Clock, Calendar, Instant, LocalDate, DayOfWeek, ZoneId).

    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
     verranno
    -0.83
     Cik
    -0.77
     seni
    -0.75
     просто
    -0.74
     aspetta
    -0.73
    条
    -0.73
    żesz
    -0.73
     nus
    -0.73
     potrebbero
    -0.72
     kuku
    -0.72
    POSITIVE LOGITS
     Calendar
    1.30
     calendar
    1.23
     getInstance
    1.17
     time
    1.13
     instance
    1.05
    getInstance
    1.01
     cal
    0.94
    Calendar
    0.93
     conocimientos
    0.92
    calendar
    0.91
    Activations Density 0.005%

    No Known Activations