© 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. 71033
    Prev
    Next
    INDEX
    Explanations

    types of style

    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
    pulseira
    -1.58
     公仔
    -1.48
    
    -1.48
     parís
    -1.47
    تول
    -1.45
     anbef
    -1.41
    慙
    -1.41
    髹
    -1.39
     imprescindible
    -1.34
     beschik
    -1.34
    POSITIVE LOGITS
     -
    1.83
    </h4>
    1.72
     style
    1.60
     same
    1.55
    </sup>
    1.54
    ”？
    1.51
     to
    1.46
    m
    1.46
     of
    1.41
     '
    1.41
    Activations Density 0.013%

    No Known Activations