© 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. 23385
    Prev
    Next
    INDEX
    Explanations

    walk-in showergeneroussoaking tub

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

    lack of perceived

    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
    懸
    0.46
    🏰
    0.40
    খানি
    0.39
    횡
    0.38
    vartheta
    0.38
    時期
    0.37
    uyor
    0.37
    বৃত্ত
    0.36
     মানবাধিকার
    0.36
    সাহিত্য
    0.36
    POSITIVE LOGITS
     ener
    0.40
     ਦੇ
    0.40
     TU
    0.38
     Energie
    0.38
     fot
    0.38
     생성
    0.37
     Converts
    0.37
     Energy
    0.37
     來
    0.37
     energi
    0.36
    Activations Density 0.000%

    No Known Activations