© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8471
    Prev
    Next
    INDEX
    Explanations

    regex quantifiers and wildcards

    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
    s
    3.73
    ా
    2.85
    ו
    2.84
    sort
    2.71
    sir
    2.58
    sı
    2.51
    ेक
    2.48
    t
    2.48
    sik
    2.32
    sides
    2.32
    POSITIVE LOGITS
    lebnis
    2.87
    ᆹ
    2.71
    ipheral
    2.54
    actif
    2.53
    lebn
    2.52
    ystring
    2.50
    Det
    2.48
    '."
    2.36
    ',"
    2.36
    ство
    2.35
    Activations Density 1.258%

    No Known Activations