© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 36923
    Prev
    Next
    INDEX
    Explanations

    major cities and capitals

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

    city names

    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_31_width_262k_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
     সীমান্তবর্তী
    0.61
    enst
    0.57
    )->
    0.53
    arid
    0.52
     сель
    0.52
    ारों
    0.52
    WUE
    0.51
    catenin
    0.50
    傈
    0.50
    een
    0.50
    POSITIVE LOGITS
     metropolitan
    0.93
     Metropolitan
    0.92
     महानगर
    0.85
     city
    0.82
     Mumbai
    0.80
    City
    0.79
     City
    0.79
     Jakarta
    0.78
     mumbai
    0.77
     cityscape
    0.75
    Activations Density 0.193%

    No Known Activations