© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1041
    Prev
    Next
    INDEX
    Explanations

    javascript code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     atof
    0.85
    ")->
    0.82
     atoi
    0.78
    :-)
    0.78
     Inet
    0.77
    hspace
    0.77
     Anosov
    0.76
     MALDI
    0.75
     $*$-
    0.74
     nonnegative
    0.73
    POSITIVE LOGITS
     !==
    2.53
     ===
    2.34
    (`${
    2.30
     `${
    2.02
    ({
    1.94
    `${
    1.94
     ||
    1.92
    !==
    1.89
     &&
    1.77
    ({...
    1.75
    Activations Density 0.006%

    No Known Activations