© 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. 21733
    Prev
    Next
    INDEX
    Explanations

    proper names and acronyms

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

    variations, life, library, interface

    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
    либо
    0.45
    вается
    0.45
    раб
    0.44
    によって
    0.43
    は
    0.43
    ளுடைய
    0.43
    ‌شده
    0.41
    ی
    0.40
    க
    0.39
    ・
    0.39
    POSITIVE LOGITS
     interface
    0.45
     www
    0.40
     도입
    0.39
     উৎসাহিত
    0.39
     teclas
    0.39
     앱
    0.38
     amulet
    0.38
    铵
    0.38
     menyiapkan
    0.38
     소개
    0.37
    Activations Density 0.000%

    No Known Activations