© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74590
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific formatting

    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
     their
    -2.22
     Depending
    -1.91
    as
    -1.91
     Despite
    -1.91
     Usually
    -1.80
     unrelenting
    -1.79
    In
    -1.79
     廠
    -1.77
     remain
    -1.76
     unruly
    -1.72
    POSITIVE LOGITS
     kapak
    2.09
    夘
    2.09
     leſs
    2.03
    ↵
    2.00
     dekoratif
    2.00
    ='')
    1.95
     rostros
    1.87
     dando
    1.87
    ˋ
    1.85
     unſ
    1.80
    Activations Density 0.061%

    No Known Activations