© 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. 118548
    Prev
    Next
    INDEX
    Explanations

    Wal-Mart and similar words

    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
    なん
    -0.89
     Saturdays
    -0.86
     loving
    -0.75
    ácií
    -0.74
     restricciones
    -0.73
    Printf
    -0.71
     Hwy
    -0.70
    THRESH
    -0.69
     wholesome
    -0.69
     ghế
    -0.68
    POSITIVE LOGITS
     Wal
    1.12
    Wal
    0.97
     WAL
    0.93
    Mart
    0.93
     Pager
    0.85
    endsection
    0.84
     mart
    0.83
     کیلومتر
    0.83
     wal
    0.81
    flower
    0.81
    Activations Density 0.014%

    No Known Activations