© 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. 105959
    Prev
    Next
    INDEX
    Explanations

    software development contexts

    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
    菝
    -1.81
     indulgent
    -1.78
     ramifications
    -1.77
    鮰
    -1.76
    觧
    -1.73
    Introducción
    -1.73
     Leur
    -1.73
    蛧
    -1.72
    饪
    -1.72
     murieron
    -1.72
    POSITIVE LOGITS
     being
    2.02
     that
    1.89
    culadora
    1.83
    なのかな
    1.77
     like
    1.77
     compete
    1.74
    andowski
    1.69
    ি
    1.69
    骉
    1.67
     misión
    1.66
    Activations Density 0.016%

    No Known Activations