© 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. 34-GEMMASCOPE-RES-131K
    7. 45521
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    The neuron is tuned to detect numeric tokens (digits, numerals, and number‐like strings) in the text.

    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
     over
    -0.79
     in
    -0.78
     re
    -0.76
     for
    -0.75
     brutal
    -0.71
    izada
    -0.70
    Editor
    -0.69
     on
    -0.69
     reduce
    -0.67
     sort
    -0.66
    POSITIVE LOGITS
    <strong>
    1.05
    gypte
    0.87
     PEG
    0.85
     harte
    0.85
    Guarantee
    0.83
    strukturen
    0.81
    小时
    0.81
    leistungs
    0.81
     emporio
    0.79
     Sailors
    0.79
    Activations Density 0.247%

    No Known Activations