© 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. 115710
    Prev
    Next
    INDEX
    Explanations

    countries and languages

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

    countries and languages

    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
     ያላቸው
    0.42
     סי
    0.39
     المصفوفه
    0.39
    献
    0.39
    רון
    0.39
    ృ
    0.39
    解説
    0.38
    ంచు
    0.38
    MiddleLine
    0.38
     ดังนั้น
    0.38
    POSITIVE LOGITS
    akers
    0.51
    hetam
    0.46
    )=
    0.44
    cede
    0.43
    also
    0.43
     kaik
    0.42
    chemical
    0.41
    tedy
    0.41
    kaj
    0.41
    oglycos
    0.41
    Activations Density 0.001%

    No Known Activations