© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22204
    Prev
    Next
    INDEX
    Explanations

    perpetuation, continuation, lasting

    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
    岖
    -2.22
     \'
    -2.22
    י
    -2.13
    䰀
    -2.11
    🧏
    -2.08
    libat
    -2.00
    所以我
    -1.99
    ⾝
    -1.98
    蹋
    -1.98
    嫲
    -1.98
    POSITIVE LOGITS
    '
    2.91
    k
    2.89
    h
    2.88
    p
    2.72
    f
    2.63
    b
    2.61
    x
    2.44
    you
    2.41
    ↵
    2.33
    c
    2.28
    Activations Density 0.007%

    No Known Activations