© 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. 237856
    Prev
    Next
    INDEX
    Explanations

    scholarship to, continue reading, tether up

    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
    uders
    0.48
    ธรรมชาติ
    0.44
     สิง
    0.44
     статистика
    0.44
    ומי
    0.44
     даль
    0.44
     มิ
    0.43
     ច
    0.43
     পারস্পরিক
    0.43
    他们在
    0.43
    POSITIVE LOGITS
     charcoal
    0.47
     damned
    0.46
     entirely
    0.45
     wholly
    0.45
     indefinitely
    0.44
     permanently
    0.44
     vague
    0.44
     tó
    0.44
     cent
    0.43
     partly
    0.43
    Activations Density 0.003%

    No Known Activations