© 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. 146840
    Prev
    Next
    INDEX
    Explanations

    specifying terms

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

    grading situation

    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
     чыныгы
    0.59
     எடுத்துக்கா
    0.48
     BENEFITS
    0.48
     பின்ன
    0.47
    誂
    0.47
     შ
    0.46
     また
    0.46
     варто
    0.46
     የበለጠ
    0.46
     さらに
    0.46
    POSITIVE LOGITS
    Logout
    0.43
     Sade
    0.43
    úan
    0.43
    NC
    0.41
    竭
    0.41
     wypeł
    0.41
     Navarre
    0.40
    Div
    0.40
    Nav
    0.39
     Logout
    0.39
    Activations Density 0.001%

    No Known Activations