© 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. 123591
    Prev
    Next
    INDEX
    Explanations

    surnames and acronyms

    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
     剤
    -3.06
    If
    -2.83
    li
    -2.83
    In
    -2.78
     美味
    -2.72
    絰
    -2.67
    lione
    -2.66
    io
    -2.55
    ‪.‬‬
    -2.47
    ᡥ
    -2.44
    POSITIVE LOGITS
     I
    3.16
    寕
    2.92
     所以
    2.77
    甃
    2.73
    的在
    2.69
    鹛
    2.66
    鹪
    2.66
    
    2.56
    𞤢
    2.53
    湏
    2.48
    Activations Density 0.019%

    No Known Activations