© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1636
    Prev
    Next
    INDEX
    Explanations

    programming data types

    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
    /#
    0.82
     सशस्त्र
    0.72
    verw
    0.72
    new
    0.72
    ottes
    0.71
     মুজিবকে
    0.71
     (#
    0.70
     (/
    0.69
    <0xE8>
    0.69
     স্বায়ত্ত
    0.69
    POSITIVE LOGITS
     int
    3.28
    int
    3.06
     float
    2.48
    float
    2.45
     boolean
    2.36
    boolean
    2.20
    double
    2.07
     double
    2.05
     char
    2.04
    char
    1.99
    Activations Density 0.090%

    No Known Activations