© 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. 12237
    Prev
    Next
    INDEX
    Explanations

    words starting with met

    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
     Thousand
    -0.73
    Particular
    -0.71
     TextInputType
    -0.69
     comunión
    -0.67
     besides
    -0.67
    ionych
    -0.67
    čo
    -0.65
    acı
    -0.64
    ungkan
    -0.63
     Colorado
    -0.63
    POSITIVE LOGITS
     Met
    1.27
    Met
    1.22
     Mete
    0.96
     Métro
    0.95
     Mets
    0.89
    MET
    0.88
    met
    0.87
     MET
    0.85
    Minutes
    0.80
    meto
    0.80
    Activations Density 0.030%

    No Known Activations