© 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. 22-GEMMASCOPE-RES-131K
    7. 65741
    Prev
    Next
    INDEX
    Explanations

    wearing clothes and accessories

    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
     \
    -3.17
    which
    -2.59
    鈰
    -2.33
     itinerario
    -2.33
    
    -2.14
     avoids
    -2.11
    〜。
    -2.11
     We
    -2.11
     beeinflussen
    -2.11
    場合
    -2.09
    POSITIVE LOGITS
    sudadera
    2.55
    羮
    2.30
     unſ
    2.23
    了一
    2.23
     セクシー
    2.13
    烀
    2.11
    
    2.05
     permettent
    2.02
    anzug
    2.00
     They
    1.99
    Activations Density 0.010%

    No Known Activations