© 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. 30761
    Prev
    Next
    INDEX
    Explanations

    for what cause

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

    health and societal issues

    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
     fett
    0.39
    ecycle
    0.38
     ٢
    0.38
     marine
    0.38
     米
    0.37
     ধারাবাহ
    0.37
    2
    0.37
     коль
    0.37
     duty
    0.36
     exhilar
    0.36
    POSITIVE LOGITS
     মেডিক্যাল
    0.52
     biện
    0.47
    Disc
    0.46
     médica
    0.46
     médicos
    0.45
    
    0.45
     मेडिकल
    0.44
    ített
    0.44
    Sud
    0.44
     المرض
    0.44
    Activations Density 0.000%

    No Known Activations