© 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. 2499
    Prev
    Next
    INDEX
    Explanations

    loop initialization or in

    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
    𝚒
    1.93
    १८
    1.83
    irem
    1.71
    empot
    1.62
    𝚜
    1.62
    醐
    1.56
    ems
    1.55
    п
    1.55
    ۶
    1.55
    г
    1.53
    POSITIVE LOGITS
    ে
    2.84
    고
    2.81
    加坡
    2.80
    에
    2.64
    る
    2.58
    ிர்
    2.54
    רץ
    2.47
    ي
    2.46
    eleaf
    2.45
    нэт
    2.42
    Activations Density 0.000%

    No Known Activations