© 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. 73345
    Prev
    Next
    INDEX
    Explanations

    materials, options, White, lied, At, thinking, farmers

    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
    lovak
    -1.05
    腑
    -0.99
     six
    -0.90
     can
    -0.86
     it
    -0.86
     Speaker
    -0.85
     Temos
    -0.84
     World
    -0.84
     month
    -0.83
     but
    -0.82
    POSITIVE LOGITS
    この日は
    1.00
     Pesto
    0.94
     étages
    0.93
    新型コロナ
    0.88
    今日は
    0.87
     Feminism
    0.86
     ファイル
    0.85
    ってみて
    0.84
     timpul
    0.84
    กำลัง
    0.83
    Activations Density 0.045%

    No Known Activations