© 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. 6732
    Prev
    Next
    INDEX
    Explanations

    people with conditions

    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
    ამის
    0.89
    걔
    0.87
     خودم
    0.86
    ړه
    0.83
     علیحد
    0.83
     শহর
    0.82
     તેનું
    0.81
    URER
    0.81
    ופה
    0.80
    ʐ
    0.79
    POSITIVE LOGITS
     histories
    1.04
     Down
    0.99
     whom
    0.93
     आपराधिक
    0.92
     demonstrable
    0.92
     nguyện
    0.91
     geçmiş
    0.91
     underlying
    0.87
     $<\
    0.87
     Below
    0.85
    Activations Density 0.185%

    No Known Activations