© 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. 201399
    Prev
    Next
    INDEX
    Explanations

    spelled backwards

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

    established, perfecting, empty states

    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
     squ
    0.51
     zv
    0.49
     suddenly
    0.49
     recently
    0.47
    オープン
    0.44
    ライブ
    0.43
    '
    0.43
    近期
    0.43
     abruptly
    0.42
     either
    0.42
    POSITIVE LOGITS
    getTransforms
    0.49
    tDBOutput
    0.47
     паци
    0.47
    acf
    0.47
    asciiPanel
    0.46
    tFileInputExcel
    0.45
    鲵
    0.45
     ئەو
    0.45
    是将
    0.44
    LuaPush
    0.44
    Activations Density 0.000%

    No Known Activations