© 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. 76292
    Prev
    Next
    INDEX
    Explanations

    Tamil Nadu and Chennai

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

    Tamil language and regions

    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
     மிசோ
    0.55
    Montana
    0.48
     மிசோரம்
    0.48
     அலெக்ஸாண்ட்
    0.48
    τικές
    0.47
     Montana
    0.46
    𝗳
    0.44
    ς
    0.44
    अधिका
    0.43
    尕
    0.43
    POSITIVE LOGITS
     Tamil
    1.20
    Tamil
    1.16
     తమిళ
    1.11
     tamil
    1.07
     तमिल
    1.05
     तमिलनाडु
    1.00
     Chennai
    0.98
    tamil
    0.97
     Coimbatore
    0.94
    Chennai
    0.93
    Activations Density 0.117%

    No Known Activations