© 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. 163714
    Prev
    Next
    INDEX
    Explanations

    residual concepts

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

    Q4_K_M

    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
    خ
    0.57
    ي
    0.50
    ب
    0.50
    ها
    0.47
    ذ
    0.47
    ع
    0.46
    ج
    0.45
    ت
    0.45
    ف
    0.44
    Property
    0.44
    POSITIVE LOGITS
    梏
    0.43
    穰
    0.43
     특정
    0.41
     obstacles
    0.41
     USING
    0.41
    도는
    0.41
     merits
    0.40
     Иң
    0.40
    டுகளில்
    0.40
    այի
    0.40
    Activations Density 0.000%

    No Known Activations