© 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. 10-GEMMASCOPE-RES-131K
    7. 186
    Prev
    Next
    INDEX
    Explanations

    ABC News and Science

    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
    ܃
    -1.88
    に行って
    -1.85
     飯店
    -1.79
    {
    -1.73
    März
    -1.71
     viviendas
    -1.71
     dispuestos
    -1.63
    齜
    -1.62
     zwart
    -1.61
     conectados
    -1.59
    POSITIVE LOGITS
     of
    2.64
    as
    2.34
    man
    2.13
    which
    1.79
    er
    1.77
    v
    1.66
     participa
    1.60
    le
    1.55
    ly
    1.52
    高的
    1.52
    Activations Density 0.036%

    No Known Activations