© 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. 8091
    Prev
    Next
    INDEX
    Explanations

    perimeter and circumference

    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
     دانشگاه
    0.43
     आयुक्त
    0.43
     رفض
    0.42
    Bathroom
    0.42
     المصفوف
    0.42
    ˧
    0.41
     پیسہ
    0.41
    实力
    0.40
    bathroom
    0.40
     jugement
    0.40
    POSITIVE LOGITS
     perimeter
    1.62
    perimeter
    1.52
     Perimeter
    1.48
     circumference
    1.42
     perímetro
    1.34
    圍
    0.90
     Circum
    0.89
    围
    0.88
     loop
    0.87
     circunferencia
    0.87
    Activations Density 0.019%

    No Known Activations