© 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. 106382
    Prev
    Next
    INDEX
    Explanations

    equilateral triangle

    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
    ترنت
    -0.80
    mName
    -0.74
    ónima
    -0.73
    vesen
    -0.73
     conserver
    -0.72
    ugen
    -0.72
    INUM
    -0.71
     vendeur
    -0.70
    meadow
    -0.70
    Lumin
    -0.69
    POSITIVE LOGITS
     triangles
    2.61
     triangle
    2.53
    triangle
    1.91
    Triangle
    1.77
     Triangle
    1.77
    Triangles
    1.56
    三角
    1.45
    triangles
    1.44
     quadrilateral
    1.32
     三角
    1.23
    Activations Density 0.029%

    No Known Activations