© 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. 220968
    Prev
    Next
    INDEX
    Explanations

    dead at, Brooke singled, Mother Nature's

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

    simple and short

    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
    ik
    0.57
     I
    0.49
    ld
    0.47
     (
    0.47
    als
    0.47
    rieb
    0.46
    ip
    0.45
     so
    0.45
    agl
    0.45
    komst
    0.44
    POSITIVE LOGITS
    బాబు
    0.55
     контора
    0.55
     价
    0.50
     variedad
    0.48
     القسمه
    0.47
     بیاکتنې
    0.47
     نداشت
    0.47
    tFileInputExcel
    0.47
     suerte
    0.47
     લાભ
    0.47
    Activations Density 0.000%

    No Known Activations