© 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. 68812
    Prev
    Next
    INDEX
    Explanations

    nursery schools and themes

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

    The neuron specifically fires on occurrences of the word “nursery.”

    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
    泐
    -3.34
    佧
    -2.94
    的在
    -2.66
    甶
    -2.59
     decidi
    -2.55
    丷
    -2.53
    鰱
    -2.53
     fortal
    -2.53
    馓
    -2.50
    
    -2.50
    POSITIVE LOGITS
    i
    2.73
     poniendo
    2.59
     buscando
    2.41
     escribiendo
    2.41
     intentando
    2.33
    </h3>
    2.30
     desarrollando
    2.28
    o
    2.28
    This
    2.23
     realizando
    2.20
    Activations Density 0.003%

    No Known Activations