© 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. 127915
    Prev
    Next
    INDEX
    Explanations

    comparison and logical operators

    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
     Even
    -1.10
    āju
    -1.09
    templateUrl
    -1.09
     and
    -1.08
    ‘
    -1.05
     A
    -1.04
    <u>
    -1.02
     time
    -1.01
     Get
    -1.01
    POSITIVE LOGITS
     verschillende
    1.37
     nieuwe
    1.17
     ebenfalls
    1.16
     prachtige
    1.14
    logotipo
    1.12
     тоже
    1.12
     bekende
    1.11
    filtre
    1.10
     både
    1.10
     langit
    1.09
    Activations Density 0.003%

    No Known Activations