© 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. 40-GEMMASCOPE-2-RES-262K
    7. 164644
    Prev
    Next
    INDEX
    Explanations

    Xi'an, Shaanxi, Northeast Mandarin, Islamic

    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_40_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
    Florida
    0.62
     Florida
    0.61
    🇭
    0.56
     FLORIDA
    0.52
    广东省
    0.51
    粵
    0.51
     Broward
    0.49
    江西
    0.48
     Miami
    0.48
    沖縄
    0.48
    POSITIVE LOGITS
     Kano
    0.59
     Muhammad
    0.56
    塬
    0.55
     Qur
    0.55
    Ƙ
    0.54
     Allah
    0.54
     Kaduna
    0.54
     Islamic
    0.54
    Islamic
    0.52
     Sahel
    0.52
    Activations Density 0.007%

    No Known Activations