© 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. 10-GEMMASCOPE-RES-131K
    4. 101629
    Prev
    Next
    INDEX
    Explanations

    Yu, Nate

    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_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
    s
    -3.91
    v
    -3.53
      
    -3.31
    -
    -3.25
    ↵
    -2.98
    this
    -2.86
    d
    -2.78
     is
    -2.78
    n
    -2.77
    <em>
    -2.70
    POSITIVE LOGITS
    喾
    2.97
     Шаг
    2.69
    ⃙
    2.56
    archiwizowane
    2.56
    垌
    2.48
     vzdu
    2.47
    erapeutics
    2.38
     když
    2.36
    鉿
    2.36
     Ответить
    2.34
    Activations Density 0.002%

    No Known Activations