© 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. 89131
    Prev
    Next
    INDEX
    Explanations

    books, online stores, testing distributions, visitors engaged

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

    handle, letting, intern, process, basic, programmed

    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
    αι
    0.45
    鈿
    0.42
    ಲ
    0.41
    кта
    0.40
     недвижимости
    0.40
    o
    0.40
    Construction
    0.40
    פ
    0.40
     впоследствии
    0.40
    ਤੀ
    0.39
    POSITIVE LOGITS
     Diagram
    0.49
     Document
    0.47
     macOS
    0.45
     phosphoryl
    0.44
     cookbook
    0.44
    了不少
    0.43
     emoji
    0.42
    outlet
    0.42
     Tasks
    0.42
     دیگه
    0.42
    Activations Density 0.000%

    No Known Activations