© 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. 2394
    Prev
    Next
    INDEX
    Explanations

    sink drains

    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
    lierung
    -0.73
    iennes
    -0.72
    elsch
    -0.67
     PopupWindow
    -0.65
    潤
    -0.64
     Шу
    -0.63
    立法
    -0.62
    resolvers
    -0.62
    rosoft
    -0.61
    lico
    -0.61
    POSITIVE LOGITS
     sink
    4.66
     sinks
    4.16
    sink
    3.89
     Sink
    3.42
    Sink
    3.39
     Sinks
    2.88
     basin
    2.17
     sinking
    2.16
     sank
    1.98
     basins
    1.96
    Activations Density 0.033%

    No Known Activations