© 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. 34-GEMMASCOPE-RES-131K
    7. 3010
    Prev
    Next
    INDEX
    Explanations

    window events

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

    The neuron is keyed to Java language keywords and tokens that occur in class or method declarations (e.g. “extends,” “implements,” “new,” “synchronized,” “void,” 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_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
     evento
    -0.81
    イベント
    -0.81
    tott
    -0.78
     falla
    -0.76
    getEvent
    -0.75
     botas
    -0.75
    Siehe
    -0.74
     tiempo
    -0.74
    žní
    -0.73
     送料
    -0.72
    POSITIVE LOGITS
     Window
    0.90
     nyingi
    0.81
    RTRS
    0.81
     Beamten
    0.80
     WINDOW
    0.79
    conceito
    0.78
    əm
    0.77
    Window
    0.76
     window
    0.76
    Item
    0.75
    Activations Density 0.003%

    No Known Activations