© 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. 130328
    Prev
    Next
    INDEX
    Explanations

    channel receive or send operations

    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
     They
    -1.80
     вони
    -1.78
    While
    -1.77
    Have
    -1.74
     @"/
    -1.73
     MEXICO
    -1.71
     而
    -1.66
     Settembre
    -1.66
     ALTER
    -1.64
     SCRIPT
    -1.62
    POSITIVE LOGITS
     internacionais
    1.86
     a
    1.79
     the
    1.79
    enablog
    1.72
     trabaja
    1.70
     fáciles
    1.67
     añadido
    1.66
     Psicología
    1.65
     además
    1.63
     invitado
    1.62
    Activations Density 0.001%

    No Known Activations