© 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. 10-GEMMASCOPE-RES-131K
    7. 61319
    Prev
    Next
    INDEX
    Explanations

    grateful for

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

    This neuron detects expressions of gratitude (e.g., “grateful”).

    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
     rouse
    -2.72
     forsake
    -2.64
    ſſi
    -2.56
     ochran
    -2.47
     relinquish
    -2.42
    Kirche
    -2.28
    翃
    -2.28
     intersper
    -2.28
    
    -2.28
    Kirchen
    -2.25
    POSITIVE LOGITS
    .“
    3.44
    an
    3.34
    “
    3.17
    ,“
    2.81
    that
    2.73
    :“
    2.70
    ing
    2.69
    but
    2.61
    ية
    2.50
     commenti
    2.44
    Activations Density 0.001%

    No Known Activations