© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19457
    Prev
    Next
    INDEX
    Explanations

    the start of descriptive phrases

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

    The neuron specifically detects occurrences of the capitalized definite article “The.”

    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
     équipements
    -1.77
    ,
    -1.75
     défis
    -1.73
     oreille
    -1.73
    Exciting
    -1.73
    癀
    -1.72
    ly
    -1.72
     rigue
    -1.71
    魠
    -1.71
     derniers
    -1.70
    POSITIVE LOGITS
     This
    2.64
     it
    2.52
     you
    2.30
     have
    2.22
     Not
    2.14
     there
    2.09
     we
    2.05
     But
    1.94
     cannot
    1.92
     Some
    1.79
    Activations Density 0.379%

    No Known Activations