© 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. 22-GEMMASCOPE-2-RES-16K
    7. 1638
    Prev
    Next
    INDEX
    Explanations

    code comments and syntax

    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_22_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
    </sub>
    0.78
     italics
    0.71
    `
    0.70
     just
    0.66
     also
    0.65
     Walsh
    0.64
    របស់
    0.63
    Popen
    0.62
    >`
    0.62
    ころ
    0.62
    POSITIVE LOGITS
    //
    2.78
     ////
    2.05
     //
    2.04
    ////
    2.00
    ///
    1.98
    //!
    1.96
    /////////////
    1.91
    //////////////
    1.89
    /*
    1.87
    ////////////
    1.87
    Activations Density 0.626%

    No Known Activations