© 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. 100533
    Prev
    Next
    INDEX
    Explanations

    cable covers, templates, instructions, confinement

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

    especially if

    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
    Сер
    0.54
    Се
    0.48
    Мар
    0.48
    Ми
    0.46
    Опера
    0.46
    შ
    0.46
    Фа
    0.45
    در
    0.45
    జ
    0.45
    Ж
    0.45
    POSITIVE LOGITS
     avec
    0.59
     moyennes
    0.56
     +-
    0.54
     confinement
    0.53
    ieu
    0.48
     pêche
    0.48
     앞
    0.48
     randon
    0.48
     crean
    0.48
     을
    0.47
    Activations Density 0.000%

    No Known Activations