© 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. 11504
    Prev
    Next
    INDEX
    Explanations

    country names

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

    countries and nationalities

    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
     இடத்தில்
    0.46
    那边
    0.45
     allí
    0.45
     dorado
    0.44
    ﺘ
    0.43
     Allí
    0.40
     viện
    0.39
     செயலாளர்
    0.39
     estavam
    0.39
     சிலையின்
    0.39
    POSITIVE LOGITS
    वासियों
    0.55
    বাসী
    0.46
    🇹
    0.45
    льні
    0.45
    телите
    0.45
    🇮
    0.45
    各地
    0.43
    Архі
    0.43
    jší
    0.43
    বাসীর
    0.42
    Activations Density 0.132%

    No Known Activations