© 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. 34-GEMMASCOPE-RES-131K
    7. 75861
    Prev
    Next
    INDEX
    Explanations

    application entry points and startup

    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
     Arzne
    -0.88
    戮
    -0.83
     frigate
    -0.83
    ਤਾ
    -0.82
    ivoli
    -0.81
     lợi
    -0.80
     aprovechar
    -0.75
     بتاريخ
    -0.75
    lavi
    -0.74
    顆
    -0.74
    POSITIVE LOGITS
    runApp
    1.23
    QApplication
    1.10
    launch
    1.04
    UIApplication
    1.00
     Launch
    0.81
    launched
    0.81
     launch
    0.80
    startGame
    0.78
     élément
    0.77
    Launcher
    0.72
    Activations Density 0.021%

    No Known Activations