© 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. 11531
    Prev
    Next
    INDEX
    Explanations

    stringent measures, getChild, setUser

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

    the word "stringent" or method calls related to getting child nodes/elements in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires strongly on occurrences of the adjective “stringent.”

    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
    This
    -4.03
    It
    -3.55
    If
    -3.48
    When
    -3.45
    A
    -3.39
    In
    -3.34
    The
    -3.30
    o
    -3.22
    t
    -3.11
    These
    -2.95
    POSITIVE LOGITS
    鱨
    3.33
    潆
    3.09
    圌
    2.91
     frequentemente
    2.80
    ῞
    2.73
    蓐
    2.70
    geſ
    2.66
    螣
    2.64
    塍
    2.63
    比较好
    2.58
    Activations Density 0.006%

    No Known Activations