© 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. 50093
    Prev
    Next
    INDEX
    Explanations

    numbers and related quantities

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

    The neuron fires strongly on numerical data—quantities, measurements, stats, or figures (numbers with or without units).

    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
     installed
    -1.00
     approach
    -0.98
     considerations
    -0.98
     upbringing
    -0.96
     attempt
    -0.96
    Toeschouwers
    -0.93
     undertaken
    -0.91
     efforts
    -0.91
    出現
    -0.91
     to
    -0.91
    POSITIVE LOGITS
     stuff
    1.01
     cantidad
    0.95
    umumkan
    0.93
     facsimile
    0.91
    孕
    0.90
    here
    0.88
     amounts
    0.88
     φορ
    0.86
    Ü
    0.85
    ômes
    0.84
    Activations Density 0.248%

    No Known Activations