© 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. 22-GEMMASCOPE-RES-131K
    7. 32570
    Prev
    Next
    INDEX
    Explanations

    code structure and punctuation

    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
    Negative Logits
    Neben
    -1.05
    stuhl
    -0.99
    setFrame
    -0.94
     neben
    -0.94
    他
    -0.93
     Conseils
    -0.92
     JUGA
    -0.90
    impan
    -0.90
    ʿ
    -0.89
    testData
    -0.88
    POSITIVE LOGITS
     again
    1.16
     for
    1.03
    部は
    0.96
     रेखा
    0.95
     خواهید
    0.94
     throughout
    0.92
    Petit
    0.91
    勝利
    0.90
    伱
    0.88
     OUTER
    0.88
    Activations Density 0.004%

    No Known Activations