© 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. 2308
    Prev
    Next
    INDEX
    Explanations

    technical descriptions, specifications, or patents

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

    method comprising

    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
     luật
    0.70
     Đảng
    0.70
    ómago
    0.69
     Luật
    0.69
    谴
    0.68
     Businessman
    0.68
    上涨
    0.67
     політи
    0.67
     Quốc
    0.64
    赎
    0.64
    POSITIVE LOGITS
     preferably
    0.98
     embodiments
    0.96
     optionally
    0.95
     substantially
    0.93
     radially
    0.88
     deformable
    0.88
    preferably
    0.86
     thermally
    0.85
     axially
    0.84
     plurality
    0.83
    Activations Density 0.145%

    No Known Activations