© 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. 79468
    Prev
    Next
    INDEX
    Explanations

    names and professions

    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
    ieR
    -1.01
     distinct
    -0.96
    portraits
    -0.95
    🕗
    -0.93
    titanium
    -0.91
    稚
    -0.91
    prese
    -0.90
    凄
    -0.90
    neuri
    -0.89
    стюм
    -0.89
    POSITIVE LOGITS
    tosis
    0.94
     яйцо
    0.93
     />\
    0.91
    переди
    0.88
    我们需要
    0.88
     utah
    0.87
     Oahu
    0.85
    jahre
    0.85
    личи
    0.85
     Nicaragua
    0.85
    Activations Density 0.000%

    No Known Activations