© 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. 34-GEMMASCOPE-RES-131K
    7. 3476
    Prev
    Next
    INDEX
    Explanations

    java graphics and ui

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

    The neuron strongly fires on Java source‐code tokens—especially punctuation and dotted method calls (e.g. “.”, “;”, “(“ and chained calls like “wnd.getContentPane()”).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Prosper
    -0.79
     Bruno
    -0.78
    瘀
    -0.75
    居然
    -0.74
     kelp
    -0.72
     paral
    -0.71
    Bruno
    -0.71
     reckon
    -0.70
    对抗
    -0.70
     Paras
    -0.69
    POSITIVE LOGITS
    repaint
    2.44
     repaint
    2.02
     paint
    1.99
     painting
    1.76
    paint
    1.71
     painted
    1.55
    Paint
    1.48
     pintura
    1.42
    painting
    1.41
     Paint
    1.38
    Activations Density 0.018%

    No Known Activations