© 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. 13783
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    erà
    2.81
     "//
    2.77
    ação
    2.75
    ০
    2.73
     ">
    2.69
    er
    2.68
    #"
    2.62
     *"
    2.61
    aaaaaaaa
    2.56
     ":
    2.54
    POSITIVE LOGITS
    ার্টমেন্ট
    2.93
    ‌هایی
    2.79
    🅐
    2.79
     ἐ
    2.73
    ‌ها
    2.67
    ębior
    2.65
    क्षत्र
    2.65
     κα
    2.63
    utacji
    2.62
    อป
    2.62
    Activations Density 0.026%

    No Known Activations