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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15163
    Prev
    Next
    INDEX
    Explanations

    history of theory and concepts

    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
    再次
    -0.94
     new
    -0.93
    GroupLayout
    -0.91
    일
    -0.88
    %
    -0.88
    tokio
    -0.85
    HomeComponent
    -0.85
    行列
    -0.84
    By
    -0.84
    再一次
    -0.84
    POSITIVE LOGITS
    🛤
    1.10
     since
    1.09
    の歴史
    1.07
     history
    1.06
     how
    1.03
     why
    1.02
     unsuccessful
    0.98
     BERNAMA
    0.98
     Entstehung
    0.94
     filós
    0.93
    Activations Density 0.094%

    No Known Activations