© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 31619
    Prev
    Next
    INDEX
    Explanations

    conjunctions and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    vasive
    0.50
    __,
    0.45
     determines
    0.45
    ถุนายน
    0.44
    ysteine
    0.42
     pentru
    0.42
    ंबकीय
    0.42
    carbons
    0.41
     eukary
    0.41
     Aquinas
    0.41
    POSITIVE LOGITS
     و
    0.67
     ও
    0.63
     மற்றும்
    0.60
    และ
    0.60
     및
    0.59
    及び
    0.57
     ਅਤੇ
    0.57
     ו
    0.56
     ಮತ್ತು
    0.55
     وأ
    0.55
    Activations Density 0.019%

    No Known Activations