© 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. 162651
    Prev
    Next
    INDEX
    Explanations

    web design, rice, scratch

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

    tiny bones, fastest routes, harming yourself

    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
    ǜ
    0.49
    Callories
    0.48
    传入
    0.48
    涣
    0.47
     disagreed
    0.47
     loafers
    0.46
    zuoye
    0.46
    Marks
    0.46
    氿
    0.45
    人员
    0.45
    POSITIVE LOGITS
    ਲੀ
    0.49
     podr
    0.46
    ੰ
    0.46
    وک
    0.45
    ivere
    0.44
    rix
    0.43
     entre
    0.42
     atual
    0.42
     despre
    0.42
    ੰਜ
    0.42
    Activations Density 0.001%

    No Known Activations