© 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. 6749
    Prev
    Next
    INDEX
    Explanations

    you'll find

    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
    ゛
    0.88
    ــــــــ
    0.88
    配套
    0.87
     tipping
    0.87
    substantial
    0.86
     kiss
    0.84
    reaching
    0.83
    ंकि
    0.82
     monumental
    0.81
    لیکن
    0.81
    POSITIVE LOGITS
     odstr
    1.08
     '%
    1.03
     '{
    1.03
     nipp
    1.00
     elem
    0.98
    elem
    0.97
    getError
    0.95
    ulina
    0.94
     Namen
    0.93
     Anfang
    0.92
    Activations Density 0.018%

    No Known Activations