© 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. 95087
    Prev
    Next
    INDEX
    Explanations

    demand and statistics

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

    counting, and questions

    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
     roy
    0.54
    vacuum
    0.49
     injure
    0.46
     abbrevi
    0.46
    udson
    0.46
     tighten
    0.46
    真空
    0.46
    _
    0.45
    यल
    0.45
     griev
    0.45
    POSITIVE LOGITS
     navegación
    0.53
     Россия
    0.49
    伲
    0.48
    ாவின்
    0.48
    сал
    0.48
    ración
    0.46
    مان
    0.46
     comentó
    0.46
     Khark
    0.46
    osynthesis
    0.46
    Activations Density 0.000%

    No Known Activations