© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83819
    Prev
    Next
    INDEX
    Explanations

    javafx and fx integration

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

    The neuron fires on mentions of “FX” (e.g. in JavaFX package or class names and import statements).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    );
    -3.50
    ).
    -3.14
    ↵
    -2.70
    {
    -2.56
     ).
    -2.52
       
    -2.27
    n
    -2.20
    d
    -2.19
    </h4>
    -2.16
    ();
    -2.14
    POSITIVE LOGITS
     帅气
    2.64
     手绘
    2.47
     cht
    2.47
     kapture
    2.44
     farba
    2.38
    橚
    2.36
    ったので
    2.33
     listos
    2.30
    蚰
    2.30
     插画
    2.25
    Activations Density 0.006%

    No Known Activations