© 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. 22-GEMMASCOPE-RES-131K
    7. 129811
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric and measurement tokens—digits, statistics, units, or other number‐related elements in text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    proper nouns and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    commons
    -0.81
    宠物
    -0.80
    нём
    -0.77
    marca
    -0.73
     during
    -0.73
    𝙻
    -0.73
    when
    -0.72
    ụ
    -0.71
     специалисты
    -0.71
    dog
    -0.69
    POSITIVE LOGITS
     customers
    0.98
     henkil
    0.91
    rugu
    0.88
     satunya
    0.83
     Вікіпе
    0.83
     henkilö
    0.82
    bev
    0.81
    álise
    0.81
     inp
    0.81
     Clientes
    0.80
    Activations Density 0.117%

    No Known Activations