© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 12913
    Prev
    Next
    INDEX
    Explanations

    urban city descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wesleyan
    0.49
    彝
    0.48
     Cnemidophorus
    0.48
     agrícolas
    0.47
    傈
    0.47
     농
    0.45
    cript
    0.45
    农
    0.44
     Nauchno
    0.43
    莪
    0.43
    POSITIVE LOGITS
     city
    1.87
     urban
    1.85
     City
    1.70
    City
    1.70
    city
    1.63
    CITY
    1.62
     CITY
    1.60
     cityscape
    1.60
    城市
    1.59
    urban
    1.58
    Activations Density 0.174%

    No Known Activations