© 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. 122593
    Prev
    Next
    INDEX
    Explanations

    products, distinguished, served, Wiki, luggage

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

    process information, services tailored

    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
    一系列
    0.48
    晚上
    0.46
    绘
    0.46
    <0xA3>
    0.45
    <0xAB>
    0.45
    aiset
    0.44
    Sobre
    0.43
    Compras
    0.43
    丞
    0.43
    ั้น
    0.43
    POSITIVE LOGITS
     Pb
    0.50
     Antarctic
    0.48
     カテゴ
    0.48
     reports
    0.46
     Theoretical
    0.46
     directs
    0.46
     Hunger
    0.46
     correlates
    0.45
     predicts
    0.45
     brownies
    0.45
    Activations Density 0.001%

    No Known Activations