© 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. 7123
    Prev
    Next
    INDEX
    Explanations

    `javax.swing` and `ModelListener`

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

    This neuron fires on programming‐related identifiers—class names, type names, method names, and other code tokens.

    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
     on
    -0.92
     with
    -0.79
     seems
    -0.76
    <
    -0.74
     came
    -0.71
    يح
    -0.69
    电视剧
    -0.66
     کاملا
    -0.66
    𝘩
    -0.65
    ерт
    -0.64
    POSITIVE LOGITS
    FAULT
    0.85
    getValueAt
    0.83
    Canal
    0.81
    簒
    0.81
    raciones
    0.80
    κος
    0.80
     leſs
    0.79
     tranſ
    0.78
     Viitattu
    0.78
    rasil
    0.77
    Activations Density 0.002%

    No Known Activations