© 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. 1593
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions and formulas

    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
     récup
    0.70
    并在
    0.66
     Kog
    0.64
    --,
    0.63
    までに
    0.62
     இவ்
    0.62
    ανα
    0.59
     Lupus
    0.58
    并
    0.58
     (${
    0.58
    POSITIVE LOGITS
    {\
    1.01
    {|\
    0.90
    {-\
    0.87
    {|
    0.87
     {\
    0.83
    {
    0.80
     {|
    0.78
    {}{
    0.77
    {-
    0.76
    {#
    0.75
    Activations Density 0.037%

    No Known Activations