© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109676
    Prev
    Next
    INDEX
    Explanations

    learning courses

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     redenen
    -0.90
     acestui
    -0.82
     khăn
    -0.79
    讥
    -0.78
     beteiligt
    -0.77
    essayer
    -0.74
    щадь
    -0.73
    ensione
    -0.73
     kleding
    -0.73
    쌤
    -0.71
    POSITIVE LOGITS
     courses
    4.31
     course
    4.28
     Course
    2.84
     Courses
    2.84
    Course
    2.81
    course
    2.78
    courses
    2.67
    Courses
    2.59
     curso
    2.38
     курс
    2.38
    Activations Density 0.059%

    No Known Activations