© 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. 10-GEMMASCOPE-RES-131K
    7. 38381
    Prev
    Next
    INDEX
    Explanations

    step-by-step instructions or analysis

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ganó
    -1.67
    {
    -1.63
     
    -1.63
    ↵↵
    -1.53
     be
    -1.49
    >
    -1.41
     at
    -1.38
    い
    -1.38
     by
    -1.38
     <
    -1.34
    POSITIVE LOGITS
    ?”
    1.95
    摀
    1.73
    :”
    1.72
    utentic
    1.70
     assurer
    1.63
    ”;
    1.63
     unsere
    1.61
    -”
    1.61
    。”
    1.60
     assister
    1.60
    Activations Density 0.006%

    No Known Activations