© 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. 100799
    Prev
    Next
    INDEX
    Explanations

    page numbers

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

    page content classification

    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
    ح
    0.62
    ח
    0.54
    f
    0.51
    हा
    0.48
    ف
    0.46
    শা
    0.46
    巫
    0.46
    ли
    0.46
     unix
    0.46
    بان
    0.46
    POSITIVE LOGITS
    щение
    0.46
    SECOND
    0.43
     Fairness
    0.43
     pisc
    0.43
     الكامل
    0.42
     SECOND
    0.42
    CISE
    0.42
     الداخلية
    0.41
    SECTION
    0.41
     බ
    0.40
    Activations Density 0.001%

    No Known Activations