© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40477
    Prev
    Next
    INDEX
    Explanations

    grateful for/to

    np_acts-logits-general · gemini-2.5-flash-lite

    The main thing this neuron does is detect expressions of gratitude or thankfulness (e.g. “grateful for…”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ка
    -1.70
    LECTIONS
    -1.66
    *}[
    -1.66
     a
    -1.63
     selten
    -1.60
     lots
    -1.57
    ть
    -1.55
     verschieden
    -1.54
    zulka
    -1.49
     forsake
    -1.49
    POSITIVE LOGITS
     would
    1.86
     that
    1.83
     
    1.66
    這
    1.65
     of
    1.58
    这种
    1.57
     superfí
    1.53
     maría
    1.50
    蒾
    1.48
    這個
    1.45
    Activations Density 0.007%

    No Known Activations