© 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. 745
    Prev
    Next
    INDEX
    Explanations

    questions and negations starting with "do"

    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
    시킨
    2.10
    ה
    1.97
    시키는
    1.97
    ی
    1.95
    원의
    1.88
    ি
    1.86
    시키
    1.82
    ا
    1.77
    ी
    1.74
    াস
    1.73
    POSITIVE LOGITS
    nt
    2.31
    sa
    1.88
    けて
    1.85
    碍
    1.83
     encanta
    1.78
    áles
    1.74
    लरशिप
    1.73
    мок
    1.70
    क्यात
    1.69
    athom
    1.69
    Activations Density 0.548%

    No Known Activations