© 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. 48103
    Prev
    Next
    INDEX
    Explanations

    sink drain pipe

    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
    ambique
    -0.82
     windscreen
    -0.81
     Qualitäts
    -0.81
    旯
    -0.78
     windshield
    -0.78
    sonian
    -0.77
     pollin
    -0.77
    Enclosure
    -0.74
    marginHorizontal
    -0.74
    Доб
    -0.73
    POSITIVE LOGITS
     drain
    1.84
     drains
    1.57
     sewer
    1.42
     sink
    1.36
     Drain
    1.35
    drain
    1.33
     Sink
    1.27
    Drain
    1.24
    sink
    1.23
     sinks
    1.19
    Activations Density 0.022%

    No Known Activations