© 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. 3560
    Prev
    Next
    INDEX
    Explanations

    contiguous United States

    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
     Galilee
    -0.93
    海の
    -0.76
    système
    -0.72
     MAH
    -0.70
     locomotives
    -0.69
     Résultat
    -0.69
    UNIDAD
    -0.69
    บอก
    -0.69
     autorizado
    -0.69
     locomotive
    -0.69
    POSITIVE LOGITS
     continental
    3.28
     Continental
    2.63
     contiguous
    2.48
    continental
    2.45
    Continental
    2.39
     CON
    2.09
     Conti
    2.08
    contiguous
    1.94
    CON
    1.70
     mainland
    1.65
    Activations Density 0.045%

    No Known Activations