© 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. 738
    Prev
    Next
    INDEX
    Explanations

    washing a cloth

    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
     Ubisoft
    0.76
     Blackjack
    0.75
    PluginResult
    0.74
    SelectSingleNode
    0.72
    懈
    0.71
    <0xB5>
    0.70
     шеран
    0.69
    splice
    0.69
    ヤモンド
    0.68
    貂
    0.67
    POSITIVE LOGITS
     containers
    3.18
     container
    3.06
    容器
    2.90
     jars
    2.77
    container
    2.76
     bowl
    2.75
     Containers
    2.74
     Container
    2.68
     bowls
    2.61
    containers
    2.54
    Activations Density 1.837%

    No Known Activations