© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11753
    Prev
    Next
    INDEX
    Explanations

    function call with `)`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    0.54
    widgetTo
    0.54
    else
    0.51
    {
    0.48
    z
    0.47
     ;
    0.47
    continue
    0.46
    next
    0.45
     {
    0.45
    delay
    0.45
    POSITIVE LOGITS
     substrates
    0.52
     denaturation
    0.49
     bowls
    0.48
     eosin
    0.48
     caloric
    0.48
     esophageal
    0.47
    孅
    0.47
     ketones
    0.45
     grooves
    0.45
     pyruvate
    0.45
    Activations Density 0.093%

    No Known Activations