© 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. 37165
    Prev
    Next
    INDEX
    Explanations

    want to

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

    what user wants

    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
    ط
    0.99
    ง
    0.96
    ق
    0.95
    ב
    0.85
    ف
    0.83
    ט
    0.81
    方法
    0.81
    ों
    0.77
    ม
    0.76
    新
    0.73
    POSITIVE LOGITS
     desires
    0.81
     desider
    0.76
    t
    0.67
     deseja
    0.66
    AnimationFrame
    0.66
     want
    0.64
     просмотра
    0.63
     deseos
    0.63
     desire
    0.61
     △
    0.61
    Activations Density 0.080%

    No Known Activations