© 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. 10-GEMMASCOPE-RES-131K
    7. 104641
    Prev
    Next
    INDEX
    Explanations

    time after manner speed basis simulations level perspective

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

    The neuron detects mentions of quantitative or numeric contexts—numbers, measurements, units, counts, and related terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     to
    -1.62
     for
    -1.36
     should
    -1.23
     znaleźć
    -1.13
     without
    -1.13
    épar
    -1.11
     sonrası
    -1.11
     Francji
    -1.10
     ilustracji
    -1.10
     razie
    -1.09
    POSITIVE LOGITS
     his
    1.31
     each
    1.31
     these
    1.29
    Ꮒ
    1.27
     dichas
    1.27
     respective
    1.22
     These
    1.20
    ∓
    1.18
     punya
    1.18
    走吧
    1.17
    Activations Density 0.742%

    No Known Activations