© 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. 49918
    Prev
    Next
    INDEX
    Explanations

    laying groundwork or foundation

    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
     gangen
    -0.93
    addLine
    -0.88
     què
    -0.87
     kubwa
    -0.84
    addHeader
    -0.82
    🖊
    -0.78
     perles
    -0.78
    
    -0.77
    Karena
    -0.75
    morgen
    -0.75
    POSITIVE LOGITS
     groundwork
    2.88
     foundation
    2.78
     pave
    2.67
     paving
    2.63
     paved
    2.55
     foundations
    2.45
     laying
    2.39
     establish
    2.22
     foreshadow
    2.22
     set
    2.16
    Activations Density 0.100%

    No Known Activations