© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129650
    Prev
    Next
    INDEX
    Explanations

    spinner UI element

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

    The neuron activates on occurrences of the term “spinner,” especially when referring to the Android UI Spinner widget.

    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
    —
    -2.83
    -
    -2.81
    1
    -2.78
    在她
    -2.77
     astonishing
    -2.70
    2
    -2.67
    In
    -2.52
    However
    -2.48
    ve
    -2.45
    在他的
    -2.45
    POSITIVE LOGITS
    身边的
    2.97
    鼙
    2.81
    怎么能
    2.66
    炱
    2.63
    ですかね
    2.61
    ZZA
    2.59
    🅃
    2.56
     urusan
    2.55
    黌
    2.53
    接下来的
    2.48
    Activations Density 0.003%

    No Known Activations