© 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. 34-GEMMASCOPE-RES-131K
    7. 87137
    Prev
    Next
    INDEX
    Explanations

    specific words following "the"

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

    The neuron strongly activates on English articles and possessive determiners (e.g. “the,” “a,” “his”).

    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
     πάν
    -0.81
    гот
    -0.79
     yaşında
    -0.78
    odyne
    -0.77
     malattia
    -0.77
    segmentation
    -0.76
     definitively
    -0.75
    OLVED
    -0.74
     enthalten
    -0.73
    ائق
    -0.73
    POSITIVE LOGITS
    月份
    0.92
    وای
    0.79
    irce
    0.79
     blí
    0.77
     nueces
    0.76
     unwritten
    0.76
     inception
    0.75
     különböző
    0.75
    繰り
    0.75
     standby
    0.73
    Activations Density 0.019%

    No Known Activations