© 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. 22-GEMMASCOPE-RES-131K
    7. 128768
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on tokens that are names of classes or interfaces in import or using statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    -1.01
    ade
    -0.94
    idad
    -0.92
     cristianismo
    -0.90
    職人
    -0.88
     ש
    -0.88
     экстра
    -0.87
     [
    -0.86
     Capabilities
    -0.86
    Особенности
    -0.86
    POSITIVE LOGITS
    ができます
    1.04
     áng
    0.95
     AirPods
    0.93
    öffnet
    0.91
    Răsp
    0.91
     ſever
    0.91
    が終わ
    0.91
    Aziz
    0.88
    Cevapla
    0.88
     hoof
    0.88
    Activations Density 0.001%

    No Known Activations