© 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-3-12B-IT
    5. 41-GEMMASCOPE-2-RES-65K
    7. 1465
    Prev
    Next
    INDEX
    Explanations

    Korean/Japanese communication

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_65k_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
    부
    0.37
    อ
    0.34
    공
    0.34
    กิน
    0.32
    UNIVERSITY
    0.32
    연
    0.31
    피
    0.31
    독
    0.31
    Publications
    0.31
    帝
    0.31
    POSITIVE LOGITS
     нюан
    0.51
     situación
    0.50
     kondisi
    0.49
     ergonom
    0.48
     situaciones
    0.48
     situations
    0.48
     sehingga
    0.47
     aspek
    0.47
     funcionalidades
    0.47
     tends
    0.46
    Activations Density 0.018%

    No Known Activations