© 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. 22-GEMMASCOPE-RES-131K
    7. 84049
    Prev
    Next
    INDEX
    Explanations

    closing punctuationmarks and special characters

    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_22/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
    gao
    -0.98
    deld
    -0.96
     Mejora
    -0.94
     TextEditing
    -0.86
    Hello
    -0.86
    ַּ
    -0.84
    ชา
    -0.83
    也被
    -0.83
    身形
    -0.82
    饅
    -0.82
    POSITIVE LOGITS
    Важно
    0.95
    Уда
    0.89
     farklı
    0.84
    tischer
    0.82
    Кроме
    0.81
     diperlukan
    0.81
     crafty
    0.81
    Или
    0.80
    Эти
    0.80
    umumkan
    0.80
    Activations Density 0.002%

    No Known Activations