© 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. 29040
    Prev
    Next
    INDEX
    Explanations

    urban and city contexts

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

    urban and city concepts

    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
    Protein
    0.52
     Protein
    0.49
    诀
    0.49
     Proteins
    0.47
    俵
    0.47
     proteína
    0.46
    朊
    0.46
     医学
    0.46
    帛
    0.46
     प्रोटीन
    0.43
    POSITIVE LOGITS
     urban
    1.98
     city
    1.79
    urban
    1.77
    城市
    1.77
     도시
    1.70
    都市
    1.69
     CITY
    1.67
     cityscape
    1.66
    CITY
    1.66
     URBAN
    1.66
    Activations Density 0.154%

    No Known Activations