© 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. 77144
    Prev
    Next
    INDEX
    Explanations

    international places and organizations

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

    vibrations to create mist

    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
    <0x0D>
    0.53
    s
    0.51
    со
    0.50
    iel
    0.47
    ;
    0.46
    О
    0.46
    bR
    0.45
    ıs
    0.43
    bg
    0.43
    his
    0.42
    POSITIVE LOGITS
     UNESCO
    0.50
     Catalonia
    0.49
     Eurovision
    0.48
     Botswana
    0.47
    國際
    0.47
     précédemment
    0.46
     국제
    0.46
     Oekra
    0.46
     बृहस्पतिवार
    0.46
     香港
    0.46
    Activations Density 0.001%

    No Known Activations