© 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. 119012
    Prev
    Next
    INDEX
    Explanations

    taking lessons or class

    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
    gts
    -0.77
     BATCH
    -0.70
    だけが
    -0.70
    erun
    -0.69
    漂亮的
    -0.68
     województwie
    -0.68
     използ
    -0.67
    σαν
    -0.67
    ération
    -0.67
     لاع
    -0.66
    POSITIVE LOGITS
     lessons
    5.28
     lesson
    3.95
    lessons
    3.81
     Lessons
    3.72
    Lessons
    3.66
     classes
    3.38
    lesson
    2.98
     Lesson
    2.75
    Lesson
    2.73
    classes
    2.56
    Activations Density 0.057%

    No Known Activations