© 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. 47215
    Prev
    Next
    INDEX
    Explanations

    comparison operators

    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
     otros
    -0.85
     their
    -0.84
     adding
    -0.83
     removing
    -0.82
     its
    -0.79
    ựu
    -0.79
     اكتوبر
    -0.78
     other
    -0.77
     applying
    -0.77
    元の
    -0.76
    POSITIVE LOGITS
     identical
    1.27
    identical
    1.05
     Iden
    1.04
    同じ
    0.96
     precedes
    0.96
     ugyan
    0.95
     precede
    0.91
    compared
    0.90
     compared
    0.89
    Same
    0.88
    Activations Density 0.027%

    No Known Activations