© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49265
    Prev
    Next
    INDEX
    Explanations

    parallel computing threads

    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
     PLAYER
    -0.79
    iong
    -0.77
     đường
    -0.76
     Compostela
    -0.73
     歳
    -0.73
    lindungi
    -0.71
     kinderen
    -0.70
    チェック
    -0.70
    Wednesday
    -0.70
     Pickle
    -0.70
    POSITIVE LOGITS
     thread
    1.27
     threads
    1.24
    thread
    1.14
    线程
    1.13
     Thread
    0.96
    threads
    0.95
    Thread
    0.92
     launch
    0.92
    Dim
    0.90
    block
    0.89
    Activations Density 0.027%

    No Known Activations