© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67661
    Prev
    Next
    INDEX
    Explanations

    UI components in code

    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_22/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
     in
    -2.27
     all
    -1.88
     for
    -1.84
     on
    -1.81
     with
    -1.77
     by
    -1.73
    を
    -1.72
     at
    -1.71
     to
    -1.65
    調味料
    -1.56
    POSITIVE LOGITS
    為に
    1.86
    久し
    1.80
    つづく
    1.77
    で見る
    1.73
    もうすぐ
    1.63
     cómodo
    1.62
    ええ
    1.61
    ਗ਼
    1.61
     confiable
    1.56
     tamaños
    1.54
    Activations Density 0.016%

    No Known Activations