© 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. 107511
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude after be verbs

    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
    zucht
    -0.85
    óra
    -0.84
    ابی
    -0.81
     carbono
    -0.79
     congratulations
    -0.77
     exciting
    -0.76
    zeni
    -0.76
    newGame
    -0.75
    NGS
    -0.75
    Exciting
    -0.73
    POSITIVE LOGITS
     grateful
    3.09
     thankful
    2.44
     gratitude
    2.25
     indebted
    2.25
     forever
    1.91
     eternally
    1.84
     dankbar
    1.69
     owe
    1.61
     благодар
    1.61
    rateful
    1.57
    Activations Density 0.019%

    No Known Activations