© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36657
    Prev
    Next
    INDEX
    Explanations

    jackson, app, framework

    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
     with
    -2.34
     in
    -2.28
     all
    -2.11
     to
    -2.08
     on
    -1.98
     from
    -1.96
     by
    -1.88
     without
    -1.83
     for
    -1.83
     because
    -1.75
    POSITIVE LOGITS
     magnificent
    1.80
    為に
    1.79
     marvelous
    1.78
    感じです
    1.68
    久し
    1.67
    もう一度
    1.63
    を探す
    1.60
     élar
    1.57
    ＊＊＊
    1.54
    ことも
    1.51
    Activations Density 0.013%

    No Known Activations