© 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. 14720
    Prev
    Next
    INDEX
    Explanations

    .com/

    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
     重量
    1.58
     χρή
    1.57
    人员
    1.54
    哪些
    1.54
    eş
    1.52
    竽
    1.51
    묽
    1.47
     个
    1.47
     定义
    1.46
    цију
    1.45
    POSITIVE LOGITS
    &#
    1.46
    oreg
    1.19
    December
    1.19
    uary
    1.18
    owski
    1.18
    बद्ध
    1.17
    #[
    1.16
    ow
    1.15
     coldly
    1.15
    ilea
    1.15
    Activations Density 0.002%

    No Known Activations