© 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. 222562
    Prev
    Next
    INDEX
    Explanations

    chiefly or principally considering

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

    keeps, quietly, or Good

    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
    '
    0.62
     n
    0.49
     tuz
    0.49
     STP
    0.48
     sawing
    0.48
     quan
    0.47
     averages
    0.47
     fum
    0.47
     pior
    0.47
     calculation
    0.47
    POSITIVE LOGITS
    响应
    0.48
     مركز
    0.46
     ঐতিহ্য
    0.46
    輙
    0.45
    癜
    0.45
    িন্দু
    0.45
    的时
    0.45
     изменя
    0.44
     центре
    0.44
     экране
    0.44
    Activations Density 0.000%

    No Known Activations