© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 5646
    Prev
    Next
    INDEX
    Explanations

    Nepal and Kathmandu

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

    Nepal, Kathmandu, government

    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_53_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
    ेंटीना
    0.52
     transatlantic
    0.49
     Covenant
    0.47
     வெப்சீரி
    0.45
    🫐
    0.45
     reefs
    0.44
     الجزائر
    0.44
    visiae
    0.44
    鳕
    0.44
    Alabama
    0.43
    POSITIVE LOGITS
     Nepal
    2.77
     Nepali
    2.73
    Nepal
    2.66
     Kathmandu
    2.55
    Nepali
    2.41
     Nep
    2.27
     नेपाल
    2.23
     नेपाली
    2.09
    Nep
    1.98
     nep
    1.91
    Activations Density 0.068%

    No Known Activations