© 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. 11652
    Prev
    Next
    INDEX
    Explanations

    Visual China

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

    part-of-speech tagging

    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
    ș
    0.43
    RESS
    0.42
    ress
    0.41
    REW
    0.40
    wagon
    0.40
     ph
    0.39
     सलाम
    0.38
    ph
    0.38
    pm
    0.38
     ding
    0.38
    POSITIVE LOGITS
    тности
    0.44
     صن
    0.38
     Bankr
    0.38
    窨
    0.38
     చి
    0.38
    аст
    0.36
     Пен
    0.36
     remanded
    0.36
    駆け
    0.36
    気の
    0.35
    Activations Density 0.037%

    No Known Activations