© 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. 81037
    Prev
    Next
    INDEX
    Explanations

    buzz, buzzes, and names like Buzzurro

    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
     Estudiantes
    -0.78
    天气
    -0.77
    投げ
    -0.75
    的东西
    -0.73
    ″
    -0.72
    んだろう
    -0.71
     gefertigt
    -0.71
     Internation
    -0.71
    嚇
    -0.71
    Sil
    -0.71
    POSITIVE LOGITS
     buzz
    1.97
     Buzz
    1.90
    buzz
    1.74
     buzzing
    1.52
    Buzz
    1.48
    🐝
    1.14
    wole
    1.09
    saw
    1.06
    feed
    1.03
     BU
    1.00
    Activations Density 0.006%

    No Known Activations