© 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. 22677
    Prev
    Next
    INDEX
    Explanations

    trips and excursions

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

    The neuron activates on words naming group outings or travel activities (e.g. trips, excursions, treks, tours, outings).

    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
    𝗟
    -1.59
     ス
    -1.57
    此前
    -1.53
    憚
    -1.45
    此处
    -1.45
    呖
    -1.45
    弐
    -1.41
     ходу
    -1.41
    もしくは
    -1.41
     ważne
    -1.39
    POSITIVE LOGITS
     to
    2.02
    1
    1.72
    齪
    1.68
    旆
    1.68
    两个
    1.66
     erweitert
    1.63
     berechtigt
    1.62
    gruppe
    1.61
    蔸
    1.47
     relish
    1.46
    Activations Density 0.014%

    No Known Activations