© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10906
    Prev
    Next
    INDEX
    Explanations

    present illness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    \<^
    1.87
    >′
    1.72
     Мар
    1.69
    ›
    1.69
     Два
    1.67
     марки
    1.67
     Ле
    1.66
     Гра
    1.65
     ۲۰
    1.63
     Ша
    1.62
    POSITIVE LOGITS
    t
    1.26
    n
    1.23
    nega
    1.21
    つまり
    1.18
    IENTO
    1.06
    すなわち
    1.05
    sheep
    1.03
    という意味
    1.02
    गारी
    0.99
    ときは
    0.99
    Activations Density 0.027%

    No Known Activations