© 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. 47110
    Prev
    Next
    INDEX
    Explanations

    constitutional referendum

    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
     citations
    -0.79
    citation
    -0.75
     perfectos
    -0.72
     citation
    -0.72
     devem
    -0.70
    追踪
    -0.70
     priser
    -0.70
     Recipients
    -0.70
     guapos
    -0.69
     шапка
    -0.69
    POSITIVE LOGITS
     referendum
    3.75
     Refer
    2.41
     refer
    2.31
    Refer
    2.13
    refer
    2.03
    REFER
    1.93
     réfé
    1.86
     plebis
    1.84
     REFER
    1.83
     ballot
    1.62
    Activations Density 0.037%

    No Known Activations