© 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-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5833
    Prev
    Next
    INDEX
    Explanations

    latex fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
     aversion
    2.66
    וא
    2.07
     involution
    1.97
     veracity
    1.95
    𝙩
    1.88
     ontology
    1.86
     преде
    1.80
    excluding
    1.80
     evaporated
    1.76
     embank
    1.75
    POSITIVE LOGITS
    {}{
    2.45
    er
    2.28
    س
    2.18
    ями
    1.97
    ための
    1.95
    торой
    1.95
    Puede
    1.94
    م
    1.90
    nze
    1.87
    ях
    1.87
    Activations Density 0.017%

    No Known Activations