© 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. 210154
    Prev
    Next
    INDEX
    Explanations

    Abraham, Joseph, smaller

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

    He shouldn't

    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
     สน
    0.48
    粟
    0.48
     Archivado
    0.46
    re
    0.45
    套装
    0.44
     Packing
    0.43
    estead
    0.42
    蜜
    0.42
     herewith
    0.41
     snuff
    0.41
    POSITIVE LOGITS
     university
    0.46
     qualifier
    0.45
     কাজী
    0.43
     stretches
    0.41
     confond
    0.41
     expertise
    0.40
     multiplicative
    0.40
     Siri
    0.39
    fieldContext
    0.39
    strnc
    0.39
    Activations Density 0.001%

    No Known Activations