© 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. 109987
    Prev
    Next
    INDEX
    Explanations

    following reports

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

    through OpenAI

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Даже
    0.39
    甚至是
    0.39
    ẳ
    0.38
     জোরে
    0.38
     Steering
    0.38
    韆
    0.38
     Ventil
    0.37
    )$:
    0.37
    includes
    0.36
    不对
    0.36
    POSITIVE LOGITS
     annan
    0.55
    その他の
    0.50
     ನಮ್ಮ
    0.49
     samma
    0.48
     tayo
    0.45
     وطن
    0.45
     ferrugineux
    0.43
    เดียวกัน
    0.43
     اسی
    0.43
     інших
    0.43
    Activations Density 0.004%

    No Known Activations