© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 130739
    Prev
    Next
    INDEX
    Explanations

    international mixed-language concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $$
    0.43
    calculations
    0.39
     liabilities
    0.39
    Calcul
    0.38
     можем
    0.37
     recommandations
    0.36
    我們可以
    0.36
     кантип
    0.36
     gavel
    0.36
    $;
    0.35
    POSITIVE LOGITS
     향
    0.39
     maat
    0.39
    DropDown
    0.38
     Startup
    0.38
    ్రమ
    0.38
     আরম্ভ
    0.38
    orientation
    0.37
    机场
    0.37
     mMap
    0.37
     Tâm
    0.37
    Activations Density 0.000%

    No Known Activations