© 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. 10-GEMMASCOPE-RES-131K
    7. 72635
    Prev
    Next
    INDEX
    Explanations

    collections and views

    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_10/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
    AL
    -1.89
    e
    -1.88
     competitivo
    -1.86
    ↵↵
    -1.85
     significativo
    -1.84
    b
    -1.79
    lapsingToolbar
    -1.73
    硨
    -1.72
    The
    -1.72
     Büyük
    -1.70
    POSITIVE LOGITS
    蕻
    2.45
    </em>
    2.27
     velho
    2.14
    </h2>
    2.03
    前面的
    2.02
     prazer
    2.00
     Поэтому
    1.92
     agradável
    1.90
    他没有
    1.88
    
    1.87
    Activations Density 0.031%

    No Known Activations