© 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. 100074
    Prev
    Next
    INDEX
    Explanations

    web page content

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "page" when it appears as part of web or document navigation and interface elements.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     you
    -2.73
    .
    -2.27
     欣赏
    -2.25
     It
    -2.19
     设计
    -2.02
     搞笑
    -1.98
     have
    -1.93
     现场
    -1.91
    西哥
    -1.83
     如何
    -1.74
    POSITIVE LOGITS
     \
    2.38
    z
    2.17
    ol
    2.16
    el
    2.14
    Зно
    2.11
    us
    2.11
    ia
    2.09
    ur
    2.08
     page
    2.06
     levit
    2.06
    Activations Density 0.035%

    No Known Activations