© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108416
    Prev
    Next
    INDEX
    Explanations

    calendar dates schedules

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    рет
    -0.77
    CASE
    -0.77
    -/**
    -0.77
    ₗ
    -0.75
    indade
    -0.75
    erade
    -0.74
    HOUR
    -0.73
     HOUR
    -0.73
    ꞉
    -0.73
     Chassis
    -0.71
    POSITIVE LOGITS
     calendar
    6.41
     calendars
    5.09
    calendar
    5.03
     Calendar
    4.91
    Calendar
    4.53
     кален
    4.09
    CALENDAR
    3.94
     CALENDAR
    3.91
     calendario
    3.73
     calend
    3.56
    Activations Density 0.066%

    No Known Activations