© 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. 12937
    Prev
    Next
    INDEX
    Explanations

    sql syntax, tools, or server

    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
    髕
    -3.27
     笔画
    -2.58
     They
    -2.56
    ᕱ
    -2.56
    AutoresizingMask
    -2.52
    鉝
    -2.39
    訁
    -2.36
    あるので
    -2.34
    ꙁ
    -2.31
    </strong>
    -2.30
    POSITIVE LOGITS
    s
    3.38
     \\
    2.75
    for
    2.52
    E
    2.50
    4
    2.44
    begin
    2.41
    \_
    2.41
     $
    2.39
    ↵
    2.38
    D
    2.34
    Activations Density 0.005%

    No Known Activations