© 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. 669
    Prev
    Next
    INDEX
    Explanations

    links and code structures

    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
    <unused325>
    0.74
    <unused305>
    0.73
    <unused994>
    0.73
    <unused515>
    0.73
    <unused358>
    0.73
    <unused406>
    0.73
     깜
    0.72
    <unused1880>
    0.71
    <unused433>
    0.70
    <unused1846>
    0.70
    POSITIVE LOGITS
    Download
    1.19
     View
    1.18
    View
    1.17
    查看
    1.16
    Browse
    1.13
    Share
    1.08
    Published
    1.07
     Download
    1.07
    Explore
    1.06
    DOWNLOAD
    1.06
    Activations Density 2.842%

    No Known Activations