© 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. 34-GEMMASCOPE-RES-131K
    4. 119209
    Prev
    Next
    INDEX
    Explanations

    Java code snippets defining methods and classes

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

    This neuron detects Java method‐parameter declarations (including their annotations, types, and punctuation) within a Spring controller signature.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    void
    -0.86
     list
    -0.85
     única
    -0.82
     ways
    -0.82
     means
    -0.82
    textContent
    -0.81
     information
    -0.79
     pathogen
    -0.78
     policies
    -0.78
    burgo
    -0.77
    POSITIVE LOGITS
    @
    1.39
     @
    1.30
     [@
    1.03
    ,@
    0.97
     Model
    0.95
     Http
    0.92
    .@
    0.90
    (@
    0.88
     HttpServlet
    0.88
     MODEL
    0.86
    Activations Density 0.004%

    No Known Activations