© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13605
    Prev
    Next
    INDEX
    Explanations

    square root of or square of

    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_31_width_16k_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
    ك
    0.70
    س
    0.57
    ف
    0.57
    ק
    0.54
    is
    0.51
    krb
    0.50
    ס
    0.50
     kuz
    0.49
    كَ
    0.49
    ة
    0.49
    POSITIVE LOGITS
     square
    0.77
     квадрат
    0.75
     quadrado
    0.73
    Square
    0.73
     squaring
    0.73
     Square
    0.71
     Squares
    0.70
     SQUARE
    0.67
     مربع
    0.65
     squre
    0.65
    Activations Density 0.142%

    No Known Activations