© 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. 5568
    Prev
    Next
    INDEX
    Explanations

    cities

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

    city names and capitals

    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
     ক্ষত্রিয়
    0.48
    氐
    0.44
     Amish
    0.41
     Cajun
    0.41
     Deuter
    0.39
     Yukawa
    0.39
     রাজাকার
    0.39
    褚
    0.39
     Welsh
    0.39
    胰
    0.38
    POSITIVE LOGITS
     서울
    3.25
    東京
    2.91
    서울
    2.91
     تهران
    2.88
     मुंबई
    2.78
     İstanbul
    2.72
     Tokyo
    2.70
     Mumbai
    2.70
     Jakarta
    2.70
     Seoul
    2.69
    Activations Density 0.852%

    No Known Activations