© 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. 61138
    Prev
    Next
    INDEX
    Explanations

    built by, in, or to

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

    This neuron activates on occurrences of the word “built” (including “builtin”).

    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
    ſtra
    -2.84
    ῞
    -2.45
    ación
    -2.39
     尔
    -2.33
    ización
    -2.31
    柃
    -2.28
    peka
    -2.22
     teh
    -2.20
    rrrr
    -2.17
    able
    -2.16
    POSITIVE LOGITS
    '
    4.53
    "
    2.73
    Now
    2.72
    Doesn
    2.58
    [
    2.56
    How
    2.48
    就
    2.47
    Could
    2.39
     They
    2.38
    Still
    2.36
    Activations Density 0.011%

    No Known Activations