© 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. 127870
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     frança
    -1.39
     parachoque
    -1.28
     camiset
    -1.23
    ه‌ی
    -1.22
     چیه
    -1.17
    雠
    -1.16
     leão
    -1.15
    izacin
    -1.13
     estadounid
    -1.08
     ahşap
    -1.08
    POSITIVE LOGITS
    ワクチン
    1.28
     are
    1.23
     is
    1.20
     succinctly
    1.17
    所以在
    1.17
     could
    1.15
     should
    1.13
    Seznam
    1.08
     bona
    1.06
     所以
    1.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.