© 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. 102150
    Prev
    Next
    INDEX
    Explanations

    ornament, ornamentation, ornamental

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

    The neuron activates on occurrences of the word “ornament” (and its derivatives like “ornamental” or “ornamentation”).

    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
    ſſel
    -2.52
     ของ
    -2.48
     usai
    -2.33
     veículo
    -2.31
    鼉
    -2.30
     acidente
    -2.28
     caminhão
    -2.20
     banho
    -2.19
    ración
    -2.19
     banheiro
    -2.17
    POSITIVE LOGITS
    ↵↵
    3.91
     ‘
    2.66
     “
    2.63
     of
    2.61
    n
    2.42
      
    2.36
     ‘‘
    2.34
    <i>
    2.31
     étab
    2.22
    峮
    2.20
    Activations Density 0.002%

    No Known Activations