© 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. 36010
    Prev
    Next
    INDEX
    Explanations

    Maharashtra / Marathi

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

    Mumbai and Maharashtra

    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
    ம்பிய
    0.45
    Arkansas
    0.44
     accret
    0.43
     Centennial
    0.43
     Kentucky
    0.43
     Provisional
    0.41
    Kentucky
    0.40
    ￢
    0.40
     Pont
    0.40
    ज्ञानिक
    0.40
    POSITIVE LOGITS
     Maharashtra
    1.19
     Marathi
    1.15
    Maharashtra
    1.13
     महाराष्ट्र
    1.05
     मराठी
    1.02
     মহারা
    1.02
    Marathi
    1.02
     Mumbai
    0.95
     মুম্ব
    0.94
    महाराष्ट्र
    0.93
    Activations Density 0.041%

    No Known Activations