© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7991
    Prev
    Next
    INDEX
    Explanations

    comma separated lists

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ătoare
    0.79
    स्‍ट
    0.77
     {"
    0.77
    acer
    0.76
     моз
    0.75
    すべて
    0.75
    {"
    0.74
     ښ
    0.73
    PrintWriter
    0.73
     boolean
    0.72
    POSITIVE LOGITS
    endosi
    1.02
    opathic
    0.92
    aund
    0.90
     Poul
    0.88
    '_
    0.85
    月的
    0.85
    原因是
    0.83
    ']:
    0.83
    elling
    0.83
    '}
    0.82
    Activations Density 0.019%

    No Known Activations