© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 3166
    Prev
    Next
    INDEX
    Explanations

    event held or attendees

    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_all/layer_41_width_262k_l0_big
    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
    ាតុ
    0.46
    ម្លៃ
    0.42
    ُو
    0.39
    ンス
    0.39
    <0x94>
    0.38
     সংসারের
    0.38
     ogen
    0.38
    รือ
    0.37
     পেঁয়
    0.37
    複
    0.37
    POSITIVE LOGITS
     held
    0.62
     개최
    0.62
     Attendees
    0.59
     Held
    0.58
    Held
    0.56
    Attendee
    0.55
     참석
    0.54
    goers
    0.54
     attendees
    0.53
    held
    0.52
    Activations Density 0.006%

    No Known Activations