© 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. 74735
    Prev
    Next
    INDEX
    Explanations

    add or append to list or collection

    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
     three
    -1.93
     be
    -1.85
     five
    -1.71
     more
    -1.62
     one
    -1.59
     that
    -1.52
     so
    -1.50
     six
    -1.48
     two
    -1.45
     seven
    -1.45
    POSITIVE LOGITS
    넵
    1.71
     accentu
    1.53
     během
    1.49
    лении
    1.47
    </h1>
    1.46
     quintessential
    1.45
    ㉔
    1.43
     culmin
    1.41
     dring
    1.41
     этих
    1.39
    Activations Density 0.002%

    No Known Activations