© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 653
    Prev
    Next
    INDEX
    Explanations

    division or ratios

    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
     former
    0.80
     Former
    0.70
     Teut
    0.69
     Dorsey
    0.69
     Noetherian
    0.62
     ܀
    0.62
     XNUMX
    0.61
     thaliana
    0.61
     circumcision
    0.61
     discontent
    0.60
    POSITIVE LOGITS
    /
    3.13
    /_
    2.76
    /{
    2.71
    /.
    2.71
    /?
    2.67
    /[
    2.66
    /...
    2.66
    /,
    2.62
    /${
    2.60
    /"
    2.57
    Activations Density 0.279%

    No Known Activations