© 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. 57025
    Prev
    Next
    INDEX
    Explanations

    particularly in

    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
    Not in Any Lists

    No Comments

    Negative Logits
     både
    -1.91
     autres
    -1.82
    both
    -1.78
     différents
    -1.57
     lainnya
    -1.55
     même
    -1.54
     both
    -1.54
     demás
    -1.47
     other
    -1.46
    ทั้ง
    -1.45
    POSITIVE LOGITS
     those
    1.91
     aquellos
    1.77
     younger
    1.69
     aquellas
    1.54
     těch
    1.45
     smaller
    1.30
     касается
    1.27
     where
    1.26
     newer
    1.26
     the
    1.25
    Activations Density 0.184%

    No Known Activations