© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127865
    Prev
    Next
    INDEX
    Explanations

    adverbs of certainty, time, or manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    
    -1.20
    țiuni
    -1.16
    harapkan
    -1.15
     pedras
    -1.14
     zdol
    -1.13
    Trang
    -1.12
     repuesto
    -1.10
     Auffassung
    -1.09
    vgili
    -1.09
    kons
    -1.09
    POSITIVE LOGITS
     which
    1.24
    y
    1.09
     but
    1.07
    。
    1.07
    for
    1.06
    而且
    1.04
    li
    1.03
    w
    1.02
    !!
    1.02
    U
    1.02
    Activations Density 0.098%

    No Known Activations