© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112277
    Prev
    Next
    INDEX
    Explanations

    data contract and api types

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

    Java annotation declarations (like `@DataContract`, `@ApiModel`, `XmlType`, `XmlAccessorType`) in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is detecting XML binding annotation keywords (e.g. javax.xml.bind.annotation.* such as XmlAccessType and XmlAccessorType).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    '
    -2.86
    。"
    -2.48
     "
    -2.36
     ("
    -2.27
    －－
    -2.25
    趼
    -2.19
    </h3>
    -2.19
    !"
    -2.17
    你和
    -2.03
    —"
    -1.99
    POSITIVE LOGITS
     Ensuring
    2.53
    ਃ
    2.42
     namor
    2.17
     However
    2.09
     But
    2.09
    硨
    2.05
    錾
    2.05
     personagens
    2.03
     Auffassung
    2.02
     Segurança
    1.96
    Activations Density 0.001%

    No Known Activations