© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6756
    Prev
    Next
    INDEX
    Explanations

    taking medications

    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_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ছাত্রী
    0.92
    撅
    0.92
    感受到
    0.87
    噘
    0.87
    osta
    0.87
    eltzer
    0.85
    alım
    0.82
    線
    0.82
    onite
    0.82
    飆
    0.81
    POSITIVE LOGITS
    文字列
    1.00
     Chunk
    0.95
    字符串
    0.93
    $(
    0.92
     EVERY
    0.89
     humanidad
    0.89
    ='',
    0.88
    Longitude
    0.88
     বাং
    0.88
     Kyrgyz
    0.88
    Activations Density 0.001%

    No Known Activations