© 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. 14674
    Prev
    Next
    INDEX
    Explanations

    structs

    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
     至
    2.46
     早
    2.27
     该
    2.21
     Địa
    2.20
     Tạo
    2.20
     Cái
    2.19
     ổ
    2.17
     Trước
    2.17
    펴
    2.15
    灑
    2.13
    POSITIVE LOGITS
     دائما
    1.72
    struktur
    1.69
    ula
    1.64
    ç
    1.63
    iong
    1.60
    abal
    1.59
    bal
    1.58
    াভাব
    1.49
    ü
    1.47
    pering
    1.43
    Activations Density 0.000%

    No Known Activations