© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58204
    Prev
    Next
    INDEX
    Explanations

    Kannada language and South Indian place names

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

    The neuron strongly fires on the structured metadata lines (e.g. the infobox-style key–value entries) rather than running prose.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ತ್ತು
    -1.09
     ಮತ್ತು
    -1.02
    optimized
    -0.95
     Arora
    -0.91
    ನ್ನು
    -0.86
    pintura
    -0.84
     tatlı
    -0.83
     nori
    -0.82
     jis
    -0.81
    Kolkata
    -0.81
    POSITIVE LOGITS
     Karnataka
    2.39
     Kannada
    2.11
     Bangalore
    1.80
     Bengaluru
    1.80
    Karn
    1.49
     Mysore
    1.44
     Mys
    1.32
    Mys
    1.17
    Bangalore
    1.16
     Dodd
    1.13
    Activations Density 0.057%

    No Known Activations