© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4884
    Prev
    Next
    INDEX
    Explanations

    North and South Korean affairs

    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
    受伤
    0.59
     该
    0.48
    媺
    0.47
     Decedent
    0.47
    手术
    0.46
    Radial
    0.46
    约翰
    0.44
    AvlTree
    0.44
    TreeMap
    0.44
    鲫
    0.44
    POSITIVE LOGITS
     Korean
    0.88
     Korea
    0.87
     korea
    0.77
     Seoul
    0.75
    Korean
    0.74
     Pyongyang
    0.73
     korean
    0.71
    Korea
    0.70
     Koreans
    0.70
     kimchi
    0.68
    Activations Density 0.020%

    No Known Activations