© 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. 75523
    Prev
    Next
    INDEX
    Explanations

    synchrotron radiation beams

    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
    enciais
    -0.91
     しょう
    -0.83
    ReadKey
    -0.82
    柢
    -0.77
     gales
    -0.76
     sculpt
    -0.76
     липня
    -0.76
    爱你
    -0.75
    kaya
    -0.75
     Senators
    -0.75
    POSITIVE LOGITS
    ynchrotron
    1.12
     bea
    1.09
     beam
    0.87
     Soleil
    0.82
     Bess
    0.79
    стве
    0.79
    GeV
    0.78
     ID
    0.77
     photon
    0.76
    radiation
    0.76
    Activations Density 0.049%

    No Known Activations