© 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. 79292
    Prev
    Next
    INDEX
    Explanations

    importance of specific topics

    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
    Not in Any Lists

    No Comments

    Negative Logits
    itä
    -1.05
    办法
    -1.03
    辦法
    -0.98
    ſures
    -0.97
    话音
    -0.97
     Cualquier
    -0.96
     dowol
    -0.96
     lenge
    -0.94
     wille
    -0.93
    έα
    -0.92
    POSITIVE LOGITS
     having
    1.93
     proper
    1.61
     properly
    1.56
     accurate
    1.54
     correctly
    1.42
     each
    1.38
     maintaining
    1.36
     good
    1.35
     adequate
    1.34
     correct
    1.33
    Activations Density 0.073%

    No Known Activations