© 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. 56717
    Prev
    Next
    INDEX
    Explanations

    identification of scientific research

    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
    subplot
    -0.92
    Former
    -0.88
    SystemColors
    -0.85
    otone
    -0.81
    助理
    -0.81
    million
    -0.81
    ordu
    -0.81
    getCurrent
    -0.79
    boBox
    -0.77
     undergraduate
    -0.77
    POSITIVE LOGITS
     girls
    0.94
     modific
    0.89
     modif
    0.88
     моди
    0.87
     diamante
    0.84
     leuke
    0.84
    앰
    0.82
     Mädchen
    0.82
    quations
    0.80
     meisjes
    0.80
    Activations Density 0.008%

    No Known Activations