© 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. 22-GEMMASCOPE-RES-131K
    7. 79698
    Prev
    Next
    INDEX
    Explanations

    plural entities/achievements

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

    This neuron detects numeric quantitative expressions—counts, measures, or statistical figures (e.g. number of medals, years spent, records, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     when
    -1.67
     because
    -1.52
     after
    -1.51
     where
    -1.38
     even
    -1.35
     this
    -1.35
     still
    -1.29
     had
    -1.26
     gets
    -1.24
     despite
    -1.21
    POSITIVE LOGITS
     både
    2.23
    both
    2.23
     both
    1.73
    ทั้ง
    1.73
     két
    1.66
     beiden
    1.63
     ambas
    1.59
     två
    1.58
    两个
    1.52
    several
    1.49
    Activations Density 0.114%

    No Known Activations