© 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. 70884
    Prev
    Next
    INDEX
    Explanations

    synonym or synonymous

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

    The neuron fires on occurrences of “synonym” (e.g. “synonyms,” “synonymously,” etc.) in the text.

    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
    derdag
    -2.19
    𐑂
    -1.89
     Abweich
    -1.80
     his
    -1.72
    pushFollow
    -1.68
    疫苗
    -1.67
    行って
    -1.63
    Reino
    -1.59
    etsk
    -1.59
    してます
    -1.59
    POSITIVE LOGITS
    </td>
    2.00
     tradução
    1.78
    *'
    1.77
    '
    1.73
    ↵↵
    1.73
    .\"
    1.70
    媜
    1.70
    ``,
    1.69
     階段
    1.69
     sebagai
    1.69
    Activations Density 0.006%

    No Known Activations