© 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. 6631
    Prev
    Next
    INDEX
    Explanations

    regex numbers and keywords

    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
    ﮄ
    2.81
    了一种
    2.62
    ۸
    2.61
    От
    2.53
    ۷
    2.48
    Ｅ
    2.45
    ۶
    2.32
    乚
    2.32
    ämään
    2.27
    ㇂
    2.27
    POSITIVE LOGITS
    al
    2.89
    l
    2.81
    o
    2.81
    n
    2.77
    ا
    2.48
    ের
    2.44
    m
    2.40
    en
    2.38
    alal
    2.36
    c
    2.29
    Activations Density 0.433%

    No Known Activations