© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1418
    Prev
    Next
    INDEX
    Explanations

    PyQt/PySide components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    <unused401>
    1.40
    vagrant
    1.38
     DevOps
    1.38
    repositories
    1.38
    ̘
    1.37
    ၣ်
    1.36
     Фургала
    1.35
    <unused1008>
    1.35
     pulleys
    1.34
     Chauhan
    1.33
    POSITIVE LOGITS
     ایسے
    0.83
    &
    0.79
     Offering
    0.73
    ®
    0.73
    B
    0.72
    let
    0.69
     Out
    0.69
    AddField
    0.69
     make
    0.69
     Item
    0.68
    Activations Density 0.037%

    No Known Activations