© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4884
    Prev
    Next
    INDEX
    Explanations

    North Korea nuclear and missile programs

    np_acts-logits-general · gemini-2.5-flash-lite

    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-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    受伤
    0.57
    媺
    0.52
     Decedent
    0.52
    手术
    0.51
    离子
    0.50
    龄
    0.49
    琍
    0.48
     потребности
    0.48
     Renal
    0.47
    蝰
    0.47
    POSITIVE LOGITS
     Pyongyang
    0.88
     Korean
    0.84
     Seoul
    0.82
     Korea
    0.81
     Koreans
    0.77
     korea
    0.77
    Seoul
    0.71
     korean
    0.69
    Korean
    0.68
     Hyun
    0.68
    Activations Density 0.020%

    No Known Activations