© 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. 53-GEMMASCOPE-2-RES-65K
    7. 5230
    Prev
    Next
    INDEX
    Explanations

    phrases before proper nouns

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

    punctuated lists introducing ideas

    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
     них
    0.55
     THEM
    0.54
    某个
    0.49
     honom
    0.49
     그걸
    0.49
    そういう
    0.48
    那位
    0.48
    :
    0.48
    那些
    0.47
     THAT
    0.46
    POSITIVE LOGITS
     albeit
    0.75
     but
    0.68
     nonché
    0.66
     오늘은
    0.64
     voilà
    0.62
     voici
    0.62
     যার
    0.61
    并在
    0.61
     tačiau
    0.61
     youll
    0.61
    Activations Density 0.146%

    No Known Activations