© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11394
    Prev
    Next
    INDEX
    Explanations

    modern [noun]

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

    modernizing or modern

    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_40_width_16k_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
    。</
    0.47
     هنگ
    0.41
     __(
    0.41
     suo
    0.41
     une
    0.40
    地点
    0.40
    <<"\
    0.39
     impor
    0.38
     $<\
    0.38
    숩
    0.38
    POSITIVE LOGITS
    izr
    0.77
     moderne
    0.75
    izing
    0.73
     modernes
    0.73
    Modern
    0.72
     modernen
    0.71
     modernos
    0.70
     MODERN
    0.70
     현대
    0.69
     модер
    0.69
    Activations Density 0.070%

    No Known Activations