© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11339
    Prev
    Next
    INDEX
    Explanations

    detailed requests

    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
    푹
    1.04
     Peg
    0.95
    ","#
    0.95
    ”，“
    0.95
    ":(
    0.95
    অর্থ
    0.94
    ед
    0.94
    ':'
    0.94
    пот
    0.93
    最初は
    0.92
    POSITIVE LOGITS
    .</
    1.57
    ).</
    1.48
    。</
    1.37
    $.}
    1.29
     أيضا
    1.24
     também
    1.24
     ulteriori
    1.23
    ئیں۔
    1.22
    ).\
    1.20
    ».
    1.15
    Activations Density 0.512%

    No Known Activations