© 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-262K
    7. 20303
    Prev
    Next
    INDEX
    Explanations

    South American nationalities and regions

    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_262k_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
     Stonehenge
    0.56
     Wynn
    0.55
     Bow
    0.55
     Burgess
    0.53
     Leigh
    0.50
    娲
    0.49
     Nathan
    0.49
     স্টোন
    0.49
     Hertfordshire
    0.48
    兖
    0.48
    POSITIVE LOGITS
     Peruvian
    1.53
     Chilean
    1.52
     Colombian
    1.48
     Venezuelan
    1.48
     Bolivia
    1.46
     Urugu
    1.45
     Boliv
    1.44
     Andean
    1.44
     Ecuadorian
    1.41
     Paraguay
    1.41
    Activations Density 0.130%

    No Known Activations