© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10079
    Prev
    Next
    INDEX
    Explanations

    viewing links and content

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

    the word "view" in instructional or navigational contexts, particularly in web interfaces and technical documentation.

    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
    ),
    -3.31
    ”,
    -2.69
     Both
    -2.38
    which
    -2.36
     When
    -2.30
    s
    -2.22
     Whenever
    -2.11
    x
    -2.11
    Both
    -2.08
     Does
    -2.06
    POSITIVE LOGITS
    苼
    2.28
    盉
    2.27
    谖
    2.22
    引用元
    2.14
    厛
    2.13
     ledig
    2.09
    蠵
    2.08
    菝
    2.06
     ñ
    2.05
     raiſ
    2.05
    Activations Density 0.012%

    No Known Activations