© 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. 79207
    Prev
    Next
    INDEX
    Explanations

    Pakistan on Friday IT Dr

    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
     {{
    -0.84
     estadounidense
    -0.81
     regresa
    -0.80
    {{
    -0.80
     угол
    -0.79
     ткань
    -0.79
     encontrarás
    -0.78
     úplně
    -0.75
    Customer
    -0.75
    inet
    -0.75
    POSITIVE LOGITS
     enorm
    1.02
     expressed
    0.87
    Strongly
    0.82
     potenti
    0.79
     入口
    0.78
    ראל
    0.77
    mları
    0.77
     talking
    0.75
     unum
    0.73
     suffered
    0.72
    Activations Density 0.013%

    No Known Activations