© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75060
    Prev
    Next
    INDEX
    Explanations

    clothing parts and fit

    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
    s
    -2.23
    </strong>
    -2.06
    </u>
    -1.83
     superfí
    -1.55
    
    -1.44
    atize
    -1.41
     イラストレーション
    -1.41
    鼱
    -1.40
     it
    -1.38
     évaluations
    -1.38
    POSITIVE LOGITS
    sukienka
    1.64
     AND
    1.63
     excelentes
    1.58
    awarkan
    1.57
     Each
    1.55
    sprzedam
    1.54
    влении
    1.52
     От
    1.48
    います
    1.48
    ","
    1.48
    Activations Density 0.006%

    No Known Activations