© 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. 41634
    Prev
    Next
    INDEX
    Explanations

    foreign/technical terms

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

    links descriptor to elaboration

    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
    حال
    0.46
     worst
    0.43
    变
    0.42
     jest
    0.42
     يعمل
    0.41
     よる
    0.41
    人员
    0.40
    徭
    0.40
     for
    0.40
    ূল
    0.40
    POSITIVE LOGITS
     клави
    0.52
     содержа
    0.48
     addr
    0.47
    センス
    0.45
     компо
    0.44
     ограничи
    0.44
     умолчанию
    0.44
     tampak
    0.43
     pinMode
    0.43
    COLOG
    0.43
    Activations Density 0.000%

    No Known Activations