© 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. 83895
    Prev
    Next
    INDEX
    Explanations

    decimal numbers

    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
     or
    -2.06
     "
    -1.84
    ,
    -1.77
     '
    -1.65
     "'
    -1.60
     Octobre
    -1.57
    section
    -1.53
    e
    -1.52
    !(:
    -1.49
    ll
    -1.47
    POSITIVE LOGITS
     pautas
    1.70
     rác
    1.68
    pedidos
    1.54
    なんですが
    1.44
     gött
    1.44
     crescente
    1.42
    Ỡ
    1.42
     riun
    1.41
     situazione
    1.41
     sekarang
    1.41
    Activations Density 0.013%

    No Known Activations