© 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. 169906
    Prev
    Next
    INDEX
    Explanations

    illness Was

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

    public domain

    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
     ક્ષ
    0.57
    杪
    0.51
     умова
    0.51
     адміністра
    0.49
     meski
    0.49
     कंडी
    0.48
    ти
    0.48
     ích
    0.48
     podmín
    0.48
    ági
    0.48
    POSITIVE LOGITS
    class
    0.51
    דור
    0.46
    <0x0D>
    0.45
    得
    0.45
    يلي
    0.45
    是
    0.44
    德
    0.44
    Schwe
    0.44
    ה
    0.44
    Reviews
    0.43
    Activations Density 0.000%

    No Known Activations