© 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. 956
    Prev
    Next
    INDEX
    Explanations

    student contexts

    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
    は
    0.46
    是
    0.45
    th
    0.43
    7
    0.43
    czas
    0.42
    ট
    0.42
    속
    0.41
    ת
    0.41
    淘宝
    0.41
    edo
    0.41
    POSITIVE LOGITS
     وطالبات
    0.90
     학생
    0.80
     الطلاب
    0.79
     छात्रा
    0.76
     Student
    0.71
     Students
    0.70
     STUDENTS
    0.69
     студент
    0.68
     学生
    0.68
     student
    0.66
    Activations Density 0.008%

    No Known Activations