© 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. 19528
    Prev
    Next
    INDEX
    Explanations

    ISO and international standards

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

    The neuron fires on the numeric portions of ISO standard identifiers (e.g. the “9001” in “ISO 9001”).

    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
     That
    -1.88
    wakilan
    -1.66
    GEBRA
    -1.55
     we
    -1.55
    淠
    -1.54
    も見
    -1.53
    推し
    -1.49
    衣裙
    -1.49
    俩
    -1.48
     Of
    -1.45
    POSITIVE LOGITS
    e
    1.78
     半袖
    1.63
    5
    1.58
    sam
    1.55
    ꜆
    1.48
    ય
    1.48
    j
    1.45
    но
    1.45
    分からない
    1.42
    櫨
    1.42
    Activations Density 0.013%

    No Known Activations