© 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. 34-GEMMASCOPE-RES-131K
    4. 60896
    Prev
    Next
    INDEX
    Explanations

    tiny house or condo

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

    The neuron detects specific numerical or quantitative information—numbers, dates, measurements, and similar numerical expressions.

    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
     enzymatic
    -0.94
     townhouse
    -0.80
     stately
    -0.79
     ilmiah
    -0.79
     бассе
    -0.77
     toddlers
    -0.75
     uzyska
    -0.74
     SAVINGS
    -0.74
     newly
    -0.73
     penerbangan
    -0.73
    POSITIVE LOGITS
    Spesifikasi
    0.97
     eco
    0.97
     Airbnb
    0.96
     dwellers
    0.96
     habitable
    0.94
     Tiny
    0.91
    Penulis
    0.91
     утеп
    0.90
    Pengertian
    0.89
     inhabit
    0.88
    Activations Density 0.032%

    No Known Activations