© 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. 246994
    Prev
    Next
    INDEX
    Explanations

    questions regarding, follow olie

    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
    나
    0.50
     똑
    0.46
    নাকে
    0.46
    力を
    0.45
     apprenticeship
    0.45
     apprentices
    0.44
     resignation
    0.43
     apprentice
    0.43
     TO
    0.42
     warmth
    0.42
    POSITIVE LOGITS
    乙方
    0.54
    f
    0.54
    m
    0.52
     Doll
    0.49
     Zij
    0.49
    product
    0.49
    sheet
    0.47
     Suárez
    0.47
    c
    0.47
    v
    0.46
    Activations Density 0.000%

    No Known Activations