© 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. 113918
    Prev
    Next
    INDEX
    Explanations

    gtk, Gtk, Gtkmm, Robbie Hanson, Samba, proteoglycan

    np_acts-logits-general · gemini-2.5-flash-lite

    references to GTK (GIMP Toolkit) programming library and software frameworks.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Not in Any Lists

    No Comments

    Negative Logits
    S
    -2.64
    {
    -2.50
     інші
    -2.44
    (
    -2.31
     selben
    -2.16
    al
    -2.14
    ↵
    -2.14
     antiques
    -2.09
     obsessive
    -2.06
    ↵↵
    -2.02
    POSITIVE LOGITS
    耵
    2.94
    which
    2.94
     been
    2.88
     recentemente
    2.83
    s
    2.81
     Reſ
    2.78
     Which
    2.75
    “
    2.73
     WHICH
    2.73
     THERE
    2.73
    Activations Density 0.042%

    No Known Activations