© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15532
    Prev
    Next
    INDEX
    Explanations

    Maharashtra Mumbai Marathi

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    仙台
    1.01
     Canberra
    0.91
    宮城県
    0.76
     Kyrgyz
    0.75
     Ottawa
    0.73
     রংপুর
    0.71
     Kyrgyzstan
    0.71
    滇
    0.70
     সিলেট
    0.69
     সিলেটের
    0.69
    POSITIVE LOGITS
     Marathi
    2.23
    Maharashtra
    2.19
     Maharashtra
    2.16
     महाराष्ट्र
    2.11
     मराठी
    2.05
     মহারা
    2.03
    Marathi
    2.00
    महाराष्ट्र
    1.90
     मुंबई
    1.78
     মুম্ব
    1.77
    Activations Density 0.055%

    No Known Activations