© 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. 1587
    Prev
    Next
    INDEX
    Explanations

    It's or It takes

    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
    ŵ
    1.90
    VI
    1.79
    huang
    1.66
    PR
    1.66
    SE
    1.64
    ปก
    1.62
     গ্যাস
    1.61
     dispos
    1.60
    hiya
    1.60
    安装
    1.58
    POSITIVE LOGITS
    ו
    2.11
    繁忙
    1.99
     phrase
    1.99
     Happened
    1.98
    MenuStrip
    1.97
    ্টর
    1.88
     fateful
    1.88
    ้า
    1.88
    وئ
    1.87
    TypeId
    1.85
    Activations Density 0.256%

    No Known Activations