© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 6611
    Prev
    Next
    INDEX
    Explanations

    course codes and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vereinigte
    0.46
    '])){
    0.45
     savon
    0.44
     iPhones
    0.44
    ']},
    0.43
    Ảnh
    0.42
    ້າງ
    0.42
     Königreich
    0.40
     investor
    0.39
     mqtt
    0.39
    POSITIVE LOGITS
     courses
    0.72
     Courses
    0.70
    课程
    0.69
     कोर्स
    0.65
     Lecture
    0.63
    Courses
    0.63
    Course
    0.63
     Intro
    0.63
    Lecture
    0.63
    2
    0.62
    Activations Density 0.002%

    No Known Activations