© 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. 73574
    Prev
    Next
    INDEX
    Explanations

    fetch next available

    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
     शामिल
    -0.89
     your
    -0.89
     כולל
    -0.88
     نکن
    -0.88
    UnsafeEnabled
    -0.85
    處理
    -0.83
     menyelesaikan
    -0.80
     dived
    -0.79
    cag
    -0.78
     към
    -0.78
    POSITIVE LOGITS
     availability
    1.22
     hasNext
    1.20
    ürn
    1.12
    availability
    1.02
     while
    0.99
     advancement
    0.98
    hasNext
    0.96
    [++
    0.95
    continuation
    0.94
     advancements
    0.93
    Activations Density 0.015%

    No Known Activations