© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111399
    Prev
    Next
    INDEX
    Explanations

    becoming roles and professions

    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
     for
    -1.91
    瑧
    -1.50
     the
    -1.47
     other
    -1.41
    หรือ
    -1.36
     every
    -1.34
     on
    -1.32
     všetky
    -1.32
     with
    -1.31
    الدرا
    -1.31
    POSITIVE LOGITS
    棡
    1.88
    гмент
    1.76
    </strong>
    1.75
    </sub>
    1.73
    犼
    1.69
    ";
    
    1.67
    ization
    1.60
    }=\
    1.59
    ሖ
    1.58
    .";
    
    1.55
    Activations Density 0.024%

    No Known Activations