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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1326
    Prev
    Next
    INDEX
    Explanations

    making dough and crust

    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
     nombreuses
    1.87
    傾向
    1.62
     nombreux
    1.61
    flowLayoutPanel
    1.60
    tsó
    1.54
    <bos>
    1.52
     Gwyn
    1.50
    getAsJsonObject
    1.49
    ियोजना
    1.47
     Bryn
    1.47
    POSITIVE LOGITS
    ，
    1.77
     车
    1.70
     στην
    1.54
     前
    1.52
     你
    1.49
     στη
    1.49
     这
    1.47
     arrived
    1.46
     就是
    1.46
     την
    1.46
    Activations Density 0.118%

    No Known Activations