© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130206
    Prev
    Next
    INDEX
    Explanations

    articles followed by specific nouns

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

    This neuron strongly activates on the definite article “the” (and its capitalized form “The”), especially in documentation comments.

    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
     aplicativos
    -1.63
     แต่
    -1.52
     produzir
    -1.47
     mehrm
    -1.41
     wahre
    -1.41
     diejenigen
    -1.40
     denselben
    -1.38
     nachfol
    -1.38
     corretamente
    -1.37
    兩個
    -1.36
    POSITIVE LOGITS
     we
    1.99
     the
    1.80
     weg
    1.40
     any
    1.36
    dijo
    1.34
    焄
    1.32
    ственные
    1.30
    年も
    1.30
     uva
    1.30
     has
    1.27
    Activations Density 0.006%

    No Known Activations