© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 120105
    Prev
    Next
    INDEX
    Explanations

    Q:

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

    The neuron activates on references to the JavaFX Scene API (e.g. imports or mentions of “javafx.scene”).

    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
     in
    -2.19
     It
    -1.77
     "
    -1.64
    -
    -1.58
     l
    -1.55
     if
    -1.52
    <h2>
    -1.52
    </i>
    -1.49
     The
    -1.45
    ];
    -1.45
    POSITIVE LOGITS
    鮠
    1.88
     tekno
    1.88
     駅前
    1.82
     复古
    1.75
     手绘
    1.75
     fuis
    1.72
     etek
    1.71
    哢
    1.70
    ucap
    1.70
    juries
    1.70
    Activations Density 0.008%

    No Known Activations