© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3818
    Prev
    Next
    INDEX
    Explanations

    argparse.ArgumentParser and add_argument

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     plug
    1.82
     检测
    1.78
     θ
    1.62
     λ
    1.60
     wound
    1.60
     φ
    1.60
     程序
    1.57
     '\
    1.56
    asel
    1.53
     ʼ
    1.52
    POSITIVE LOGITS
    közi
    1.77
     niezwy
    1.66
     jedno
    1.63
     timp
    1.60
     mnoho
    1.58
    कीय
    1.57
    극한
    1.56
     období
    1.56
     حديث
    1.52
    jeni
    1.50
    Activations Density 0.002%

    No Known Activations