© 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. 14258
    Prev
    Next
    INDEX
    Explanations

    java imports and classes

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

    The neuron consistently fires on Java standard-library class names in import statements (e.g. File, IOException, ArrayList, Scanner, 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
     a
    -2.03
     trabajando
    -1.82
     to
    -1.77
     all
    -1.73
                
    -1.70
     двумя
    -1.69
     much
    -1.64
    了自己
    -1.64
     "
    -1.63
    一切都
    -1.62
    POSITIVE LOGITS
    <bos>
    2.23
    isesta
    1.63
    饜
    1.57
     fides
    1.54
    uyasha
    1.53
    ↵↵
    1.52
     whoſe
    1.52
    ꜥ
    1.52
    trui
    1.52
    greSQL
    1.52
    Activations Density 0.065%

    No Known Activations