© 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. 67457
    Prev
    Next
    INDEX
    Explanations

    kilo prefix, units

    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
    屃
    -2.02
    ﹍﹍
    -1.97
    ௅
    -1.96
     höl
    -1.91
    淠
    -1.90
    ྄
    -1.83
    
    -1.80
     jesús
    -1.79
    鹩
    -1.78
    鈈
    -1.77
    POSITIVE LOGITS
    ”
    1.85
    所有
    1.85
    0
    1.81
    4
    1.76
     of
    1.75
    8
    1.73
    有
    1.66
    l
    1.66
    mography
    1.58
    ์
    1.56
    Activations Density 0.020%

    No Known Activations