© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1659
    Prev
    Next
    INDEX
    Explanations

    brand names and platforms

    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_17_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
     priesthood
    0.90
     escapar
    0.90
    หาคม
    0.84
     critique
    0.78
    inerary
    0.78
    녀
    0.78
     narrative
    0.77
     представления
    0.75
     воспомина
    0.75
    밈
    0.75
    POSITIVE LOGITS
     subsidiaries
    1.61
     شركة
    1.56
     شركات
    1.51
    Brands
    1.51
     Telecom
    1.51
     компаний
    1.51
     şirket
    1.50
     Holdings
    1.50
     şirk
    1.49
    Telecom
    1.47
    Activations Density 1.346%

    No Known Activations