© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2976
    Prev
    Next
    INDEX
    Explanations

    event function arguments

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     williams
    0.43
    BESCHREIBUNG
    0.43
    슌
    0.41
    Williams
    0.40
    求解
    0.40
    뷊
    0.39
    RequestListener
    0.39
    
    0.39
     WILLIAMS
    0.39
    洗浄
    0.38
    POSITIVE LOGITS
     event
    1.69
    event
    1.43
     Event
    1.25
     evento
    1.25
    イベント
    1.22
     événement
    1.18
     이벤트
    1.16
     e
    1.15
    Event
    1.14
     events
    1.14
    Activations Density 0.014%

    No Known Activations