© 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. 1785
    Prev
    Next
    INDEX
    Explanations

    older driver, big adventure

    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
    ₩
    -1.59
    小型
    -1.45
     Здесь
    -1.44
     الصيف
    -1.44
    wrights
    -1.42
    数十
    -1.41
     égard
    -1.40
    ⭐
    -1.39
     ваш
    -1.38
     hav
    -1.36
    POSITIVE LOGITS
    实力
    1.59
    </td>
    1.56
    ajuku
    1.55
     começar
    1.55
     you
    1.54
     viață
    1.52
     calitate
    1.52
    耵
    1.50
     către
    1.45
    	
    1.41
    Activations Density 0.000%

    No Known Activations