© 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. 138544
    Prev
    Next
    INDEX
    Explanations

    immigrant friendly countries

    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
    ي
    0.50
     bruta
    0.46
     conformidad
    0.43
     категорії
    0.43
     prejudicial
    0.42
    鉭
    0.41
     جري
    0.41
    ום
    0.41
     статистики
    0.40
    푞
    0.40
    POSITIVE LOGITS
     તેની
    0.43
    仕組み
    0.41
    其
    0.41
     Jiang
    0.40
    elihat
    0.40
     tun
    0.38
     Guo
    0.38
    HCR
    0.38
     akan
    0.38
     sedang
    0.38
    Activations Density 0.010%

    No Known Activations