© 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. 17467
    Prev
    Next
    INDEX
    Explanations

    Russian cities and financial terms

    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
    urètre
    0.57
     statunitense
    0.57
     Chirurgien
    0.52
    nière
    0.51
     lancéolées
    0.50
    篑
    0.49
    ণ্ট
    0.49
    atients
    0.48
    🏈
    0.48
    ⛎
    0.47
    POSITIVE LOGITS
     Moscow
    0.78
     интернет
    0.78
     А
    0.77
     С
    0.73
     Novosibirsk
    0.72
     Т
    0.72
     Москов
    0.72
     Russian
    0.70
     за
    0.70
     М
    0.69
    Activations Density 0.034%

    No Known Activations