© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113244
    Prev
    Next
    INDEX
    Explanations

    en-US language code

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

    The neuron fires on the “US” language/region tag (e.g. in “en-US”) commonly embedded in URLs or documentation metadata.

    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
     it
    -2.00
     in
    -1.71
     have
    -1.69
     believed
    -1.65
     placed
    -1.62
     Of
    -1.58
     to
    -1.56
     supplying
    -1.56
     told
    -1.54
     then
    -1.48
    POSITIVE LOGITS
    These
    2.19
    这些
    2.11
    他
    2.03
    3
    1.98
    7
    1.97
    0
    1.86
    "
    1.77
    6
    1.75
    這些
    1.74
    ‟
    1.72
    Activations Density 0.005%

    No Known Activations