© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4156
    Prev
    Next
    INDEX
    Explanations

    closing bracket url

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    ۰۰
    3.12
    𝑙
    2.91
    𝑒
    2.81
    mények
    2.69
    𝑑
    2.68
    𝑣
    2.68
    𝑠
    2.55
    ר
    2.50
    न्द्रीय
    2.48
    ें
    2.42
    POSITIVE LOGITS
    ">{
    2.67
     {"
    2.64
    çük
    2.57
    {}",
    2.55
    )\\
    2.54
    𝐢
    2.37
    !/"
    2.37
    ிய
    2.34
    𝓹
    2.31
    𝓸
    2.27
    Activations Density 1.259%

    No Known Activations