© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118540
    Prev
    Next
    INDEX
    Explanations

    Hyderabad and Telangana

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Slovenia
    -0.86
     McKe
    -0.84
     tubo
    -0.78
    usehen
    -0.78
     Oficina
    -0.76
    теше
    -0.76
    נון
    -0.75
     oport
    -0.75
    isław
    -0.73
    ージェ
    -0.73
    POSITIVE LOGITS
     Hyderabad
    1.81
     Telangana
    1.72
    Hyderabad
    1.61
     Illinois
    1.13
    derabad
    1.09
    Illinois
    1.09
     Peoria
    1.08
    Tel
    0.93
    Chicago
    0.92
     Bloomington
    0.88
    Activations Density 0.013%

    No Known Activations