© 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. 90766
    Prev
    Next
    INDEX
    Explanations

    the only one/ones

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

    The neuron fires on the standalone numeral/pronoun “one” (and its plural form “ones”).

    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
    These
    -2.27
    }$
    -2.20
    They
    -2.17
    ↵↵
    -2.16
    许多
    -2.14
    There
    -2.00
    我们的
    -1.95
    Хороший
    -1.94
    Both
    -1.91
    かなり
    -1.91
    POSITIVE LOGITS
    eronau
    1.99
     they
    1.77
    有助
    1.74
    queous
    1.74
     we
    1.66
     alpes
    1.65
    桫
    1.63
     to
    1.62
    を含
    1.62
     of
    1.58
    Activations Density 0.003%

    No Known Activations