© 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. 235835
    Prev
    Next
    INDEX
    Explanations

    salt lamp

    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
     capsule
    0.54
     cloves
    0.50
     AND
    0.49
     crispy
    0.47
    {
    0.47
    в
    0.46
    িন
    0.46
     melon
    0.46
    สำคัญ
    0.46
    ็ค
    0.45
    POSITIVE LOGITS
    镤
    0.48
     Alicante
    0.46
    手里
    0.45
     Петер
    0.45
     بالق
    0.44
     здравоохра
    0.44
     Нов
    0.43
    市场上
    0.43
     मंजूर
    0.43
    दाता
    0.42
    Activations Density 0.000%

    No Known Activations