© 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. 58880
    Prev
    Next
    INDEX
    Explanations

    class definitions and machine learning terms

    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
    Hamlet
    -0.98
    idencia
    -0.79
    .--
    -0.79
    addContainerGap
    -0.79
     meson
    -0.78
     )}$
    -0.78
     Salón
    -0.78
     選手
    -0.78
     Fuerza
    -0.77
     rubio
    -0.77
    POSITIVE LOGITS
     červená
    0.88
     modrá
    0.88
    ního
    0.88
     jums
    0.87
     书
    0.85
    дне
    0.84
    ordes
    0.81
     Sutton
    0.81
     ridge
    0.81
    laut
    0.80
    Activations Density 0.007%

    No Known Activations