© 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. 56077
    Prev
    Next
    INDEX
    Explanations

    awe, marvel, wonder, admiration

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

    The neuron responds to words that express strong emotional reactions—especially awe, wonder, fear, marvel, admiration, or astonishment.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     sweetest
    -0.80
    一听
    -0.80
    บาย
    -0.77
    bpm
    -0.75
     substitution
    -0.74
    Epit
    -0.74
    canakan
    -0.73
     temperature
    -0.71
    ActivityResult
    -0.70
     yı
    -0.70
    POSITIVE LOGITS
     awe
    3.28
     marvel
    3.03
     amazement
    2.80
     wonder
    2.77
     amazed
    2.75
    awe
    2.45
     admiration
    2.17
     marvels
    2.06
    marvel
    1.98
     fascinated
    1.98
    Activations Density 0.045%

    No Known Activations