© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4280
    Prev
    Next
    INDEX
    Explanations

    place names ending in Twp or City

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

    US place names followed by settlement types

    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
     kür
    0.42
     Psik
    0.41
    광역시
    0.40
     রাজধানী
    0.40
     capital
    0.39
     ekspl
    0.39
     Biochim
    0.39
     ç
    0.38
     Başkan
    0.38
     capitals
    0.38
    POSITIVE LOGITS
     Twp
    0.82
     Township
    0.75
     township
    0.62
     Junction
    0.58
     Heights
    0.56
     Corners
    0.55
     Village
    0.54
    Village
    0.54
    Arkansas
    0.53
     Acres
    0.52
    Activations Density 0.222%

    No Known Activations