© 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. 100697
    Prev
    Next
    INDEX
    Explanations

    saved them or efficiently and safely

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

    code and structured text

    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
    ado
    0.47
    frame
    0.46
    Est
    0.45
    rahmen
    0.44
    ك
    0.44
    accur
    0.44
    ey
    0.44
    bol
    0.44
    ní
    0.44
    ade
    0.43
    POSITIVE LOGITS
     yattha
    0.52
     apes
    0.49
    ларни
    0.48
    辘
    0.48
    []');
    0.48
    。)
    0.48
     aquilo
    0.47
    ுமா
    0.47
     मर्
    0.46
    ską
    0.46
    Activations Density 0.000%

    No Known Activations