© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 102213
    Prev
    Next
    INDEX
    Explanations

    final copy or test

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

    champion to defend

    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
    အောင်
    0.47
    beauty
    0.46
     baloncesto
    0.46
     Сла
    0.46
    ج
    0.46
     حين
    0.44
     சித்த
    0.43
    تين
    0.43
    وين
    0.43
    CTAssert
    0.43
    POSITIVE LOGITS
     McCabe
    0.47
     งาน
    0.45
     niemals
    0.45
     riverside
    0.45
     still
    0.44
    袮
    0.44
     $\%
    0.44
     Mugh
    0.43
     Used
    0.43
     Abril
    0.43
    Activations Density 0.000%

    No Known Activations