© 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. 383
    Prev
    Next
    INDEX
    Explanations

    programming languages mixed with foreign words

    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
     backing
    -0.79
    உ
    -0.79
    الأ
    -0.78
    outputStream
    -0.78
    רו
    -0.77
    galkan
    -0.77
     choisir
    -0.77
    工事
    -0.77
    íná
    -0.77
    ষ
    -0.76
    POSITIVE LOGITS
     Herak
    0.89
    DRY
    0.79
    лючение
    0.75
     그의
    0.75
     downstairs
    0.74
    logías
    0.74
    迷惑
    0.71
     réservation
    0.69
    コスパ
    0.69
     Stavanger
    0.67
    Activations Density 0.024%

    No Known Activations