© 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. 53-GEMMASCOPE-2-RES-65K
    7. 7689
    Prev
    Next
    INDEX
    Explanations

    North followed by places

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

    north korea

    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_53_width_65k_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
     آس
    0.46
    南部
    0.43
     southeast
    0.42
     Oost
    0.41
    southeast
    0.41
     southwest
    0.40
     ಸಂಪ
    0.39
    东
    0.39
     OAS
    0.38
    唦
    0.38
    POSITIVE LOGITS
     Korea
    0.49
    朝鮮
    0.48
    umbria
    0.48
     Corea
    0.45
     korea
    0.45
    icosia
    0.45
     Kore
    0.45
     North
    0.43
     kore
    0.43
    ouveau
    0.42
    Activations Density 0.024%

    No Known Activations