© 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. 60719
    Prev
    Next
    INDEX
    Explanations

    escaping characters

    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
     唯美
    -2.11
     sexe
    -2.09
     eſſ
    -2.06
     插图
    -2.06
    跸
    -2.03
    躥
    -1.99
    餿
    -1.97
    髕
    -1.97
     activit
    -1.95
     抠
    -1.95
    POSITIVE LOGITS
    ↵
    3.06
     time
    2.16
    ’
    2.08
    For
    1.95
    To
    1.91
    e
    1.91
    One
    1.88
    7
    1.80
     laajenta
    1.80
    Because
    1.78
    Activations Density 0.013%

    No Known Activations