© 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. 153236
    Prev
    Next
    INDEX
    Explanations

    common word pairings

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

    pump blood

    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
    Negative Logits
    案件
    0.48
     sientes
    0.45
    ಗ್
    0.44
    估
    0.44
    拒
    0.43
    ís
    0.42
    屍
    0.42
    影片
    0.41
    弊
    0.41
    极大
    0.40
    POSITIVE LOGITS
     DAY
    0.49
     TYPE
    0.47
    Year
    0.45
    に行って
    0.45
     YEAR
    0.44
    poetry
    0.44
    year
    0.43
     -
    0.42
    จักร
    0.42
    iolet
    0.42
    Activations Density 0.000%

    No Known Activations