© 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-IT
    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-it/resid_post/layer_29_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
    #.
    0.83
    /#
    0.80
    াধিকার
    0.77
    #-
    0.75
    ージュ
    0.73
    "-
    0.70
     স্বায়ত্ত
    0.70
    หรับ
    0.69
    <0xB4>
    0.69
    ధ
    0.69
    POSITIVE LOGITS
     int
    3.13
    int
    3.06
    float
    2.70
     float
    2.59
    double
    2.20
    bool
    2.13
     double
    2.12
     bool
    2.06
     uint
    1.99
    char
    1.91
    Activations Density 0.656%

    No Known Activations