© 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. 105571
    Prev
    Next
    INDEX
    Explanations

    both or each followed by noun

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

    This neuron detects binary quantifier constructions—words that refer to two items in tandem (e.g. “both,” “each,” “either”).

    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
    ほとん
    -1.46
    さんへ
    -1.40
    even
    -1.37
     nawet
    -1.30
     櫻
    -1.30
     mesmo
    -1.29
    やう
    -1.28
     всі
    -1.28
     even
    -1.27
     намного
    -1.26
    POSITIVE LOGITS
     are
    1.42
     have
    1.39
     butterknife
    1.38
     was
    1.34
     has
    1.34
     свои
    1.33
     получили
    1.27
    是
    1.26
    chenke
    1.24
     был
    1.22
    Activations Density 0.078%

    No Known Activations