© 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. 22-GEMMASCOPE-RES-131K
    7. 12807
    Prev
    Next
    INDEX
    Explanations

    the + proper noun

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

    This neuron strongly activates on occurrences of 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_22/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
    bex
    -1.33
    ared
    -1.31
    
    -1.30
    沵
    -1.27
    athed
    -1.27
     pourraient
    -1.27
     CLAIMS
    -1.27
    actéristi
    -1.27
    aret
    -1.24
    aned
    -1.23
    POSITIVE LOGITS
     or
    1.66
     children
    1.41
     two
    1.22
     three
    1.16
     will
    1.14
     Two
    1.13
     Those
    1.12
     particularly
    1.10
     Children
    1.09
     Three
    1.07
    Activations Density 0.001%

    No Known Activations