© 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. 250003
    Prev
    Next
    INDEX
    Explanations

    specific concepts and terms

    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
    商人
    0.45
    pmm
    0.45
    プリ
    0.42
    мі
    0.41
     альтерна
    0.41
    izem
    0.41
    num
    0.41
     tries
    0.41
    ᴾ
    0.40
    少
    0.40
    POSITIVE LOGITS
     breat
    0.56
     nombreux
    0.51
     Immunology
    0.50
     Bio
    0.48
     Medicinal
    0.47
     Microbiology
    0.47
     vigt
    0.47
     Filtration
    0.47
     imbib
    0.46
     dissip
    0.46
    Activations Density 0.000%

    No Known Activations