© 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. 129859
    Prev
    Next
    INDEX
    Explanations

    ul followed by punctuation or code

    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
    かなぁ
    -2.53
     ubica
    -2.45
    な感じ
    -2.38
     Mathemat
    -2.33
    ですかね
    -2.28
     After
    -2.28
    焉
    -2.28
     queridos
    -2.22
    kac
    -2.22
    しますが
    -2.19
    POSITIVE LOGITS
    ul
    3.77
    l
    3.53
    s
    3.45
    r
    3.38
    “
    3.23
    1
    2.94
    `
    2.88
    𓆜
    2.69
    ？
    2.67
    ‘
    2.61
    Activations Density 0.015%

    No Known Activations