© 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. 6855
    Prev
    Next
    INDEX
    Explanations

    East Asian place names and brands

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

    moving average

    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
    允許
    0.42
    زى
    0.41
     simplifying
    0.39
     quil
    0.39
     Deane
    0.38
    躬
    0.38
    經典
    0.36
     ఉత్త
    0.36
    嬰
    0.36
    㐱
    0.36
    POSITIVE LOGITS
     dong
    0.64
    dong
    0.53
    Dong
    0.50
    guan
    0.47
    hae
    0.45
    댕
    0.45
     Dong
    0.44
    tat
    0.41
    辄
    0.40
    fang
    0.40
    Activations Density 0.006%

    No Known Activations