© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 17045
    Prev
    Next
    INDEX
    Explanations

    code structure and keywords

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

    function definition, macro, or loop start

    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
    ม่
    0.40
    ्राम
    0.39
    دهای
    0.38
     Cage
    0.38
    ++);
    0.37
    σκε
    0.37
     seguenti
    0.37
    ésie
    0.37
    );*/
    0.36
    เท้า
    0.36
    POSITIVE LOGITS
     factorización
    0.47
     結果
    0.44
     什么
    0.44
     」,
    0.43
    (',')
    0.41
    特徴
    0.40
     buddhav
    0.40
     принцип
    0.39
     何
    0.38
     bienvenidas
    0.38
    Activations Density 0.001%

    No Known Activations