© 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. 78519
    Prev
    Next
    INDEX
    Explanations

    eBook, consultation, etc

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

    where questions and statements

    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
    预防
    0.49
     Campylobacter
    0.47
     Gosudarstvennyj
    0.45
     averigu
    0.45
    侥
    0.43
    Mkv
    0.43
    ilyen
    0.42
     गिन
    0.42
    完璧
    0.42
    тировать
    0.42
    POSITIVE LOGITS
    sapp
    0.54
     erster
    0.53
     اہلِ
    0.50
     cả
    0.50
    language
    0.49
     ಎ
    0.49
     اہل
    0.47
     lưu
    0.47
    א
    0.47
    sair
    0.46
    Activations Density 0.001%

    No Known Activations