© 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. 99702
    Prev
    Next
    INDEX
    Explanations

    for example, for instance, inter alia

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

    The main thing this neuron does is detect phrases that introduce examples or elaborations (e.g. “for example,” “for instance,” “inter alia”).

    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
     and
    -2.03
     &
    -1.83
     But
    -1.66
    Награды
    -1.66
     belki
    -1.65
     this
    -1.64
     However
    -1.64
     clogged
    -1.60
     OF
    -1.59
    作って
    -1.55
    POSITIVE LOGITS
    “
    2.34
     You
    1.98
    —“
    1.97
    u
    1.94
    </h3>
    1.91
    -“
    1.90
    de
    1.88
    ,“
    1.84
    which
    1.83
     čtyř
    1.75
    Activations Density 0.006%

    No Known Activations