© 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. 274
    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
    ৩
    0.91
     ২
    0.85
    ২
    0.72
    ১
    0.69
     ۲
    0.68
     ১
    0.67
     tsa
    0.64
     doe
    0.63
    ০০০
    0.63
     ٣
    0.62
    POSITIVE LOGITS
    <unused2116>
    1.21
    <unused1857>
    1.17
    XX
    1.10
    世纪
    1.10
    世紀
    1.03
     веке
    1.03
    <unused1751>
    1.02
    th
    0.98
    <unused2158>
    0.98
    <unused1661>
    0.97
    Activations Density 0.649%

    No Known Activations