© 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. 25022
    Prev
    Next
    INDEX
    Explanations

    people who or in

    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
    不必
    -2.36
    \
    -2.27
    ྂ
    -2.25
    大概
    -2.22
    щита
    -2.14
     vielen
    -2.05
     sont
    -2.03
     ollut
    -1.98
     need
    -1.97
     evidenced
    -1.92
    POSITIVE LOGITS
     parachoque
    2.64
    鮰
    2.59
    というわけで
    2.59
    そういえば
    2.58
    也将
    2.50
     広場
    2.45
    グルト
    2.44
    躂
    2.44
    余談
    2.42
    hauled
    2.38
    Activations Density 0.045%

    No Known Activations