© 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. 34-GEMMASCOPE-RES-131K
    7. 106162
    Prev
    Next
    INDEX
    Explanations

    duo or pair names

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     singled
    -0.94
     sozinho
    -0.91
     solo
    -0.89
     alone
    -0.88
    三种
    -0.82
    solo
    -0.79
     singles
    -0.79
     groupings
    -0.77
     solitude
    -0.76
    ཨ
    -0.76
    POSITIVE LOGITS
     duo
    1.88
    duo
    1.54
     Duo
    1.37
     duos
    1.27
    Duo
    1.27
     duet
    1.23
     tandem
    1.22
     dupla
    1.20
    这对
    1.20
     their
    1.16
    Activations Density 0.060%

    No Known Activations