© 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. 127316
    Prev
    Next
    INDEX
    Explanations

    phrases with "put the"

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

    This neuron primarily detects the 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
     they
    -2.25
    她
    -2.16
    他
    -2.13
    
    -1.93
     dezelve
    -1.92
    for
    -1.91
    說
    -1.84
     eet
    -1.83
    be
    -1.82
    
    -1.80
    POSITIVE LOGITS
    </strong>
    2.56
    </h4>
    1.87
    糨
    1.84
    ’)
    1.77
     Fläche
    1.73
     Pflanze
    1.73
     Eigentümer
    1.70
     utilizing
    1.67
     emphasizing
    1.66
     emphasizes
    1.66
    Activations Density 0.023%

    No Known Activations