© 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. 106225
    Prev
    Next
    INDEX
    Explanations

    latex packages

    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
     Sonn
    -0.85
    资
    -0.77
    ávají
    -0.76
     continues
    -0.76
     densité
    -0.74
     الح
    -0.73
    [_
    -0.72
    GetName
    -0.72
    上线
    -0.72
    owników
    -0.69
    POSITIVE LOGITS
    graphicx
    0.94
     ändert
    0.81
    optimal
    0.80
     régionales
    0.78
     lác
    0.77
    artement
    0.77
    nahmen
    0.75
    ILEY
    0.74
    amsmath
    0.73
    Chili
    0.73
    Activations Density 0.001%

    No Known Activations