© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 48288
    Prev
    Next
    INDEX
    Explanations

    hypotonia, series, Bauhaus, Confuciusornis, Steiner

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

    The neuron is tuned to pick out long, multi-syllabic technical or proper-name terms (e.g. Diophantine, Fourier, Confucius, Steiner).

    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
    
    -2.23
    
    -2.19
    they
    -2.05
    跸
    -2.03
    Ꮉ
    -2.03
    
    -1.98
    灕
    -1.95
    इटम
    -1.88
     夜景
    -1.83
    鬭
    -1.83
    POSITIVE LOGITS
     It
    1.95
     You
    1.95
     großem
    1.66
     atractiva
    1.66
    <td>
    1.66
     Hinblick
    1.63
     guapa
    1.62
     acoged
    1.60
     help
    1.57
     Meilleures
    1.55
    Activations Density 0.004%

    No Known Activations