© 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. 13-GEMMASCOPE-2-RES-16K
    7. 10053
    Prev
    Next
    INDEX
    Explanations

    date and time formats

    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_13_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
     대한민국
    1.13
     waterfront
    1.00
     大
    0.97
     arts
    0.97
     B
    0.96
     中国
    0.94
     한국
    0.94
    一个
    0.93
    第五
    0.93
     nationwide
    0.92
    POSITIVE LOGITS
    ohy
    1.22
    ኀ
    1.17
    byteArray
    1.16
    ipy
    1.16
    resar
    1.15
    yset
    1.13
    ittä
    1.13
    iffy
    1.10
    waża
    1.09
    apour
    1.09
    Activations Density 0.019%

    No Known Activations