© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 13760
    Prev
    Next
    INDEX
    Explanations

    numerical arrays and data types

    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
    UseDebug
    0.53
    财政
    0.52
    费用
    0.51
     请求
    0.51
     Auction
    0.50
    ลด
    0.50
     громад
    0.50
    驻
    0.49
    Auction
    0.49
    高志森
    0.49
    POSITIVE LOGITS
    numpy
    0.97
     numpy
    0.94
     scipy
    0.81
     NumPy
    0.79
     Numpy
    0.72
     dtype
    0.71
    ndarray
    0.71
     np
    0.69
     ice
    0.69
     vectorized
    0.63
    Activations Density 0.336%

    No Known Activations