© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92901
    Prev
    Next
    INDEX
    Explanations

    academic courses or classes

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

    The neuron responds strongly to high‐frequency function words (common stopwords like “this,” “in,” “the,” “for,” 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
    coleg
    -0.80
    Exemplo
    -0.79
    どこに
    -0.79
    ARROLLO
    -0.74
    Resumo
    -0.74
     Bethesda
    -0.73
    Прият
    -0.72
    comuna
    -0.72
    Capacidad
    -0.72
     anoche
    -0.71
    POSITIVE LOGITS
     courses
    5.09
     course
    4.75
    courses
    3.45
     classes
    3.38
    Course
    3.34
     Courses
    3.33
    course
    3.28
    Courses
    3.25
     Course
    2.98
    课程
    2.89
    Activations Density 0.077%

    No Known Activations