© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9016
    Prev
    Next
    INDEX
    Explanations

    table summarizing

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

    The neuron detects references to numbered document elements (e.g. “Table X,” “Figure Y,” “Block Z”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    م
    0.81
    लक्ष
    0.79
    ल
    0.74
    mpi
    0.74
    ImageView
    0.66
    Image
    0.64
    Ảnh
    0.64
    刑
    0.64
     পেছন
    0.64
     জ্ব
    0.63
    POSITIVE LOGITS
     temperatures
    0.77
    歉
    0.77
     했습니다
    0.72
    onka
    0.71
    めて
    0.71
     Frankfort
    0.70
    avait
    0.70
     carpets
    0.70
    sendStatus
    0.69
    ulkar
    0.68
    Activations Density 0.075%

    No Known Activations