© 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. 103770
    Prev
    Next
    INDEX
    Explanations

    WiX Toolset MSI packages

    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
     Transparen
    -0.77
     Zacks
    -0.75
    alus
    -0.73
    Expires
    -0.73
    фер
    -0.73
    autoload
    -0.72
    OnClickListener
    -0.71
     Worcestershire
    -0.71
    一杯
    -0.69
    uttosto
    -0.69
    POSITIVE LOGITS
    MSI
    0.98
    msi
    0.95
     msi
    0.85
     MSI
    0.84
    ویش
    0.84
     quieter
    0.82
     product
    0.80
     bootstra
    0.78
    penser
    0.78
    immig
    0.77
    Activations Density 0.071%

    No Known Activations