© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 207266
    Prev
    Next
    INDEX
    Explanations

    non-english characters or words

    np_acts-logits-general · gemini-2.5-flash-lite

    fundamentally rebuilt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     reflected
    0.52
     equipped
    0.47
     observers
    0.47
     tabs
    0.47
     firearms
    0.46
    reflected
    0.46
     inputted
    0.45
     can
    0.45
    /
    0.45
     reflecting
    0.44
    POSITIVE LOGITS
     kristall
    0.57
     prü
    0.52
     새로
    0.51
     кръ
    0.50
    උ
    0.50
     především
    0.49
     제한
    0.49
     sätt
    0.49
     الجديد
    0.48
     més
    0.47
    Activations Density 0.001%

    No Known Activations