© 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. 115597
    Prev
    Next
    INDEX
    Explanations

    code comments and structure

    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
     我
    -0.76
    tól
    -0.76
     ao
    -0.76
     有
    -0.73
     diverse
    -0.73
     дола
    -0.72
     altri
    -0.71
     spoiled
    -0.71
     clásica
    -0.71
    肥料
    -0.70
    POSITIVE LOGITS
     assistente
    0.82
     Eleg
    0.81
     새로운
    0.80
     jang
    0.80
     ống
    0.79
     obicei
    0.79
    ień
    0.78
     Jef
    0.77
    odem
    0.77
    creates
    0.76
    Activations Density 0.002%

    No Known Activations