© 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. 60156
    Prev
    Next
    INDEX
    Explanations

    each and every

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

    The neuron activates on words used in quantitative or statistical contexts—terms describing counts, rates, or figures in data-driven statements.

    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
     periodically
    -1.73
    Periodic
    -1.52
     periodic
    -1.45
    periodic
    -1.43
     Periodic
    -1.39
    annual
    -1.38
     periodical
    -1.36
     mornings
    -1.35
     annual
    -1.30
     annually
    -1.26
    POSITIVE LOGITS
     each
    1.62
     every
    1.10
     каждом
    1.05
     fiecare
    1.02
     всеки
    0.98
     каждый
    0.95
     كل
    0.95
     varje
    0.93
     chaque
    0.91
    每个
    0.90
    Activations Density 0.050%

    No Known Activations