© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 4767
    Prev
    Next
    INDEX
    Explanations

    events, conferences, tournaments, competitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     development
    0.50
    io
    0.48
    it
    0.45
    ia
    0.44
     precision
    0.43
    e
    0.43
    ل
    0.43
    达
    0.43
    ur
    0.42
     Cartesian
    0.42
    POSITIVE LOGITS
     참석
    0.71
     പങ്കെടു
    0.63
     Teilnahme
    0.61
    に参加
    0.60
     attendee
    0.59
     Festivals
    0.59
     festivals
    0.58
    參與
    0.57
     참여
    0.55
     мероприятия
    0.55
    Activations Density 0.138%

    No Known Activations