© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 170365
    Prev
    Next
    INDEX
    Explanations

    childbearing, birth, origin

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

    sound money

    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_262k_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
    ൂപ
    0.49
     ملت
    0.47
    穆
    0.45
    እንደ
    0.45
    粛
    0.45
    ُمْ
    0.44
     بف
    0.44
     اسم
    0.43
     హె
    0.42
    人に
    0.42
    POSITIVE LOGITS
    c
    0.58
    cake
    0.56
     cak
    0.52
    cakes
    0.51
    ers
    0.50
    че
    0.49
     atraer
    0.49
    쮿
    0.49
    ástico
    0.49
    layer
    0.48
    Activations Density 0.000%

    No Known Activations