© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99790
    Prev
    Next
    INDEX
    Explanations

    tech companies and services

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

    The neuron fires on the names of web mapping/data‐service providers (e.g. “baidu,” “google,” “高德,” 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_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
    我们
    -1.78
    在我
    -1.74
    但是
    -1.67
    The
    -1.66
     errori
    -1.61
     beeind
    -1.57
    世界
    -1.55
     dergleichen
    -1.52
     tanpa
    -1.48
     ยัง
    -1.48
    POSITIVE LOGITS
     are
    1.91
    ↵↵
    1.55
    :
    1.52
    /
    1.52
    ⡪
    1.51
    ’
    1.45
     martin
    1.29
     and
    1.29
    arv
    1.29
    of
    1.28
    Activations Density 0.013%

    No Known Activations