© 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. 34-GEMMASCOPE-RES-131K
    7. 102365
    Prev
    Next
    INDEX
    Explanations

    following or changing course

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

    The neuron fires on language describing navigation or trajectories—terms like “off course,” “charting a course,” “flight control,” etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    égories
    -0.75
    صدر
    -0.74
    flasche
    -0.73
    Учитель
    -0.69
    വി
    -0.68
     учитель
    -0.67
    Shu
    -0.67
    ื่อน
    -0.66
    vskip
    -0.66
    スキ
    -0.65
    POSITIVE LOGITS
     course
    5.00
    course
    3.64
     Course
    3.53
    Course
    3.44
     COURSE
    3.34
    COURSE
    3.00
     курс
    2.95
     courses
    2.83
     direction
    2.53
     kurs
    2.42
    Activations Density 0.032%

    No Known Activations