© 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. 58001
    Prev
    Next
    INDEX
    Explanations

    ESPN promos

    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
    pecabe
    -1.91
    ikusbot
    -1.75
    felpa
    -1.70
    鹚
    -1.66
    makeat
    -1.66
     legjobb
    -1.62
    ୪
    -1.54
     meskipun
    -1.54
    hatenablog
    -1.53
    枥
    -1.52
    POSITIVE LOGITS
    !
    2.27
    0
    1.68
     (
    1.67
    .
    1.48
     you
    1.45
     {
    1.45
     Its
    1.42
     〜
    1.39
    tidig
    1.38
    !」
    1.35
    Activations Density 0.001%

    No Known Activations