© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69266
    Prev
    Next
    INDEX
    Explanations

    The name Russell

    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
    特斯拉
    -2.98
    剮
    -2.83
    UGHTER
    -2.73
    纐
    -2.69
     fisuras
    -2.47
    푡
    -2.45
    釙
    -2.44
     форми
    -2.42
    鈈
    -2.42
     možnosti
    -2.41
    POSITIVE LOGITS
    what
    3.03
    $
    2.86
     Some
    2.66
    6
    2.66
    3
    2.59
    2.58
     Many
    2.55
    2.52
    m
    2.52
     vertes
    2.52
    Activations Density 0.002%

    No Known Activations