© 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. 111725
    Prev
    Next
    INDEX
    Explanations

    namely

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

    hazard analysis

    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
    然后
    0.50
    Modal
    0.47
    ;
    0.47
    ）
    0.47
    ড
    0.46
    _)
    0.46
    Response
    0.45
    Solutions
    0.45
     然后
    0.44
     tecnologie
    0.44
    POSITIVE LOGITS
     இருவரும்
    0.47
     közvet
    0.44
    ㄈ
    0.44
     เล
    0.44
     Buf
    0.43
     карь
    0.43
     अनलॉक
    0.43
     linearly
    0.43
    zv
    0.43
     doubly
    0.42
    Activations Density 0.002%

    No Known Activations