© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 119296
    Prev
    Next
    INDEX
    Explanations

    activity or choice

    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_34/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
    页面
    -1.12
     página
    -1.07
    ページ
    -0.88
     homepage
    -0.88
    页
    -0.86
    頁
    -0.86
     страницы
    -0.85
    回到
    -0.82
    stricken
    -0.82
     currentPage
    -0.81
    POSITIVE LOGITS
     choose
    1.90
     Choose
    1.59
    Choose
    1.59
     choosing
    1.53
     chọn
    1.52
     chooses
    1.51
    choose
    1.46
    选择
    1.46
     elegir
    1.35
     chose
    1.34
    Activations Density 0.015%

    No Known Activations