© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16208
    Prev
    Next
    INDEX
    Explanations

    math and coefficients

    np_acts-logits-general · gemini-2.5-flash-lite

    mathematical and scientific weights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     नौकरी
    0.62
     숫
    0.59
     नौकरियों
    0.59
    上涨
    0.58
    赚钱
    0.58
     नाम
    0.57
     시작
    0.57
    宾
    0.57
    數字
    0.56
    파일명
    0.55
    POSITIVE LOGITS
     coefficients
    0.85
     plasma
    0.75
     coefficient
    0.74
     equation
    0.73
     coeff
    0.71
    coeffs
    0.69
     constants
    0.68
     sqrt
    0.67
     coeffs
    0.67
     physics
    0.65
    Activations Density 0.007%

    No Known Activations