© 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. 101329
    Prev
    Next
    INDEX
    Explanations

    JsonProperty DataMember XmlElement

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

    annotations or attributes used for JSON serialization and data contracts in code.

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

    The neuron strongly fires on serialization‐related annotation names (e.g. JsonProperty, JsonPropertyName, DataContract/DataMember, XmlAccessorType/XmlElement, 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_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
    ка
    -1.58
    with
    -1.54
    providedIn
    -1.49
    𝑛
    -1.39
    is
    -1.37
    are
    -1.35
     afir
    -1.34
    in
    -1.34
    );
    -1.34
    </u>
    -1.33
    POSITIVE LOGITS
     jetzt
    1.61
     sanitarias
    1.58
     Again
    1.47
     первый
    1.45
     estatales
    1.41
    INDICE
    1.35
     денег
    1.34
     сейчас
    1.34
    条目
    1.34
     머
    1.34
    Activations Density 0.009%

    No Known Activations