© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 14278
    Prev
    Next
    INDEX
    Explanations

    cities and urban areas

    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
    强调
    0.46
     предлага
    0.46
    鈁
    0.45
    诺
    0.44
    亿美元
    0.44
    ﹂
    0.44
    镐
    0.44
    镖
    0.44
    locatorType
    0.44
    玦
    0.44
    POSITIVE LOGITS
    city
    0.53
    City
    0.52
     city
    0.50
    都市
    0.48
    u
    0.47
    al
    0.45
     ciudades
    0.44
    p
    0.44
     cities
    0.44
    homes
    0.44
    Activations Density 0.009%

    No Known Activations