© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3899
    Prev
    Next
    INDEX
    Explanations

    korea versions and patterns

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

    Korean words and phrases

    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
    اکي
    0.54
    ្អ
    0.50
     succumbed
    0.49
    者を
    0.49
     unjustified
    0.49
     Pupils
    0.49
    缈
    0.48
     discredited
    0.48
    чается
    0.48
     assistenza
    0.47
    POSITIVE LOGITS
     korea
    1.56
     가
    1.48
     Korea
    1.48
     그
    1.45
     김
    1.45
     한국
    1.45
     서울
    1.45
     기
    1.42
     소
    1.41
     선
    1.41
    Activations Density 0.176%

    No Known Activations