© 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. 83578
    Prev
    Next
    INDEX
    Explanations

    Telugu movie and place names

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

    Hyderabad, Andhra Pradesh, Telugu

    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
     மிசோரம்
    0.56
     బ్రిటిషు
    0.54
     ಆನಿ
    0.49
     conoscenza
    0.48
    沙
    0.47
    刀
    0.47
    Often
    0.46
    及
    0.46
    碎
    0.45
    物品
    0.45
    POSITIVE LOGITS
    Telugu
    0.74
     Telugu
    0.72
     आंध्र
    0.65
     తెలుగు
    0.64
     तेलंगाना
    0.64
     तेलु
    0.63
     Kannada
    0.55
     তেলে
    0.54
     Telangana
    0.54
     cranking
    0.53
    Activations Density 0.167%

    No Known Activations