© 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. 13490
    Prev
    Next
    INDEX
    Explanations

    printing json data

    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
    ützt
    1.46
    ئة
    1.38
     "=",
    1.35
     Source
    1.34
     மீ
    1.29
     گر
    1.29
     source
    1.29
    比亚
    1.27
    ésére
    1.26
    美元
    1.25
    POSITIVE LOGITS
    ObjectHideFlags
    1.92
    taining
    1.72
    enco
    1.68
    imani
    1.67
    \{{}\
    1.67
    orithms
    1.67
    顺利
    1.67
    ens
    1.66
    cheon
    1.64
    gur
    1.62
    Activations Density 0.049%

    No Known Activations