© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58118
    Prev
    Next
    INDEX
    Explanations

    verb followed by preposition

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

    This neuron detects formal patent‐style technical descriptions, especially passages detailing invention fields, device components, and their operation (e.g., “light emitting,” “OLED,” “Field of the Invention”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     aben
    -2.02
     anun
    -1.95
     ヶ
    -1.73
     megane
    -1.73
     noss
    -1.68
     limita
    -1.68
     vost
    -1.66
     noft
    -1.63
     papan
    -1.61
     Igles
    -1.59
    POSITIVE LOGITS
    了一些
    1.68
     liés
    1.63
     nová
    1.50
     '
    1.44
    了自己的
    1.42
     stále
    1.40
    refront
    1.36
     inolvid
    1.34
    寂寞
    1.34
     большого
    1.32
    Activations Density 22.966%

    No Known Activations