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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1670
    Prev
    Next
    INDEX
    Explanations

    research into rust and decay

    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
    ៉
    3.77
    اً
    3.37
    lerinden
    2.90
    leri
    2.87
    ៉ុ
    2.78
    lardan
    2.75
    larından
    2.68
    lerini
    2.67
    fasst
    2.63
    lara
    2.58
    POSITIVE LOGITS
    ו
    3.04
    एं
    2.96
    स्फी
    2.75
    おります
    2.73
    ฿
    2.66
     beneficio
    2.65
    おしゃれ
    2.62
    お知らせ
    2.61
    с
    2.61
    お得
    2.61
    Activations Density 0.414%

    No Known Activations