© 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-65K
    7. 4503
    Prev
    Next
    INDEX
    Explanations

    triggering notifications

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ул
    0.45
     strlen
    0.40
     指
    0.40
     Defined
    0.39
     Aqueous
    0.39
    agiarism
    0.39
    鹽
    0.38
    sizeof
    0.37
     tokenizer
    0.37
    賈
    0.37
    POSITIVE LOGITS
     notify
    0.87
    notify
    0.77
     emit
    0.75
    emit
    0.74
     notifies
    0.71
     trigger
    0.70
     notifying
    0.69
    Notify
    0.69
     send
    0.68
    通知
    0.66
    Activations Density 0.105%

    No Known Activations