© 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. 34-GEMMASCOPE-RES-131K
    7. 102759
    Prev
    Next
    INDEX
    Explanations

    words ending in ran or intran

    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
    上课
    -0.80
    варь
    -0.79
     товары
    -0.74
    掲示
    -0.73
     товаров
    -0.73
     elegantes
    -0.73
     sấy
    -0.73
    kabel
    -0.73
     ビール
    -0.71
    
    -0.71
    POSITIVE LOGITS
    佑
    0.71
    zęd
    0.70
    jeans
    0.69
    らかに
    0.69
    )))
    0.68
    ⊆
    0.68
    ь
    0.68
    藐
    0.68
    общение
    0.68
     basta
    0.68
    Activations Density 0.050%

    No Known Activations