© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3627
    Prev
    Next
    INDEX
    Explanations

    discussing, exploring, or highlighting aspects

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

    explaining aspects or how

    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
     ಒಳ್ಳೆಯ
    0.18
     Nhưng
    0.18
    io
    0.17
     파일을
    0.17
     ၁
    0.17
     ತೆಗೆದುಕೊಳ್ಳ
    0.16
     ɔ
    0.16
    を使う
    0.16
    ファイルを
    0.16
     ܐ
    0.15
    POSITIVE LOGITS
    The
    0.27
     the
    0.24
    the
    0.24
     различные
    0.23
     aspectos
    0.22
     how
    0.22
    ה
    0.22
     особенностей
    0.21
     aspects
    0.21
     injustices
    0.21
    Activations Density 1.235%

    No Known Activations