© 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. 345
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     produzir
    0.82
     ресурсов
    0.81
     สอน
    0.81
     morphism
    0.76
     วิชา
    0.76
     تحليل
    0.75
     項
    0.73
     מר
    0.73
    ="../../../../
    0.72
     produire
    0.71
    POSITIVE LOGITS
     booked
    2.12
     booking
    1.92
    booked
    1.71
     ordered
    1.70
     ordering
    1.61
     Booking
    1.61
     purchased
    1.60
    booking
    1.59
    Booking
    1.58
     purchase
    1.57
    Activations Density 2.554%

    No Known Activations