© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 279
    Prev
    Next
    INDEX
    Explanations

    X-UA-Compatible

    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
    他自己
    -0.67
    ђу
    -0.66
    Rie
    -0.66
    âmara
    -0.63
    ruecos
    -0.62
    chapel
    -0.62
     III
    -0.62
    COMPONENT
    -0.61
    읽
    -0.61
    fruit
    -0.60
    POSITIVE LOGITS
    macos
    0.71
    ёр
    0.71
    ISTE
    0.68
     Content
    0.68
     Contents
    0.67
    ۔۔
    0.67
     nanos
    0.67
    Content
    0.66
    getManager
    0.66
     brach
    0.66
    Activations Density 0.049%

    No Known Activations