© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1420
    Prev
    Next
    INDEX
    Explanations

    numbers in scientific notation

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

    The neuron is a detector for numeric tokens—any standalone numbers or digit sequences (years, measurements, counts, etc.).

    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
     головой
    -0.79
    térature
    -0.75
    īt
    -0.73
    pág
    -0.72
     shouldn
    -0.71
     systemctl
    -0.71
    视着
    -0.68
    knecht
    -0.67
     sir
    -0.66
     ले
    -0.66
    POSITIVE LOGITS
    ↘
    0.96
     inferiore
    0.95
    zestaw
    0.91
     reduced
    0.88
    Reduced
    0.82
     mengurangi
    0.81
     metade
    0.81
     Shorter
    0.81
     کمتر
    0.81
    Less
    0.81
    Activations Density 0.309%

    No Known Activations