© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112760
    Prev
    Next
    INDEX
    Explanations

    package declaration

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

    Java and Spring framework configuration code, particularly package declarations, annotations, and XML configuration elements.

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

    The neuron fires on Spring configuration keywords (XML elements or annotations) such as component-scan, annotation-driven, RequestMapping/Mapping, Enable…, 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
    hObject
    -1.33
     dä
    -1.32
    龃
    -1.30
    fledged
    -1.27
     eftersom
    -1.26
     länge
    -1.23
    seite
    -1.23
    ॰
    -1.21
    ómico
    -1.19
    uint
    -1.16
    POSITIVE LOGITS
     not
    1.76
     those
    1.38
     namely
    1.36
     the
    1.32
     his
    1.31
     Cię
    1.24
    Év
    1.23
     then
    1.21
     next
    1.20
     similar
    1.19
    Activations Density 0.060%

    No Known Activations