© 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. 11713
    Prev
    Next
    INDEX
    Explanations

    requests, proposals, orders, vouchers

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

    CITIC Securities

    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
     ‘
    0.45
    ,“
    0.44
     بی‌
    0.43
    鼈
    0.42
    orkan
    0.41
     пережи
    0.41
    ור
    0.41
    ulloch
    0.40
    ,”
    0.39
     якщо
    0.39
    POSITIVE LOGITS
     encapsulates
    0.50
    Utils
    0.47
    驻
    0.47
     embod
    0.44
     exporter
    0.44
    ែម
    0.44
     Utils
    0.44
    ডাক্ট
    0.43
    Brightness
    0.43
     மாசுபடுத்த
    0.42
    Activations Density 0.000%

    No Known Activations