© 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. 85886
    Prev
    Next
    INDEX
    Explanations

    pronouns and auxiliaries

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

    The neuron is selectively activating on common function words—especially pronouns (I, she, it) and auxiliary/modal verbs (have, should, may, though, not).

    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
     clás
    -1.91
     даже
    -1.91
    лы
    -1.75
     не
    -1.75
    久しぶり
    -1.69
    刽
    -1.60
     divertidos
    -1.55
     sieht
    -1.54
    戦い
    -1.53
    桀
    -1.53
    POSITIVE LOGITS
    '
    2.09
    weilen
    1.88
    1
    1.77
     to
    1.63
    することは
    1.61
    camion
    1.59
     You
    1.59
    [
    1.48
    0
    1.48
    mathrm
    1.48
    Activations Density 0.010%

    No Known Activations