© 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. 73515
    Prev
    Next
    INDEX
    Explanations

    bridal party and dresses

    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
    ↵
    -2.31
    <strong>
    -2.28
     ‘
    -2.16
    n
    -2.06
    </em>
    -2.03
    '
    -2.03
    ’
    -2.03
            
    -2.00
    <em>
    -1.88
    f
    -1.88
    POSITIVE LOGITS
     verdaderos
    1.99
     faſt
    1.98
    媗
    1.92
    
    1.85
    罴
    1.82
    鹟
    1.77
    秋季
    1.73
    蟊
    1.73
    
    1.71
    
    1.71
    Activations Density 0.009%

    No Known Activations