© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28019
    Prev
    Next
    INDEX
    Explanations

    Java XML binding

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects Java XML‐binding (JAXB) import and annotation tokens (e.g. javax.xml.bind, XmlAccessorType, JAXB, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     leichte
    -1.29
    於
    -1.18
    {~
    -1.16
    }=
    -1.13
     zostało
    -1.12
     and
    -1.10
    stoy
    -1.10
    WriteLine
    -1.09
    :][
    -1.06
    omez
    -1.06
    POSITIVE LOGITS
    <bos>
    1.36
     êtres
    1.23
    的对象
    1.21
    补偿
    1.21
    saveData
    1.20
     besoins
    1.17
     個室
    1.13
     ター
    1.13
    jerc
    1.13
    Erro
    1.12
    Activations Density 0.005%

    No Known Activations