© 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. 123601
    Prev
    Next
    INDEX
    Explanations

    research laboratories and institutions

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

    names of national laboratories and research institutions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates most strongly on institution or organization names (e.g., laboratory or division names) in author‐affiliation metadata.

    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
    usschuss
    -1.29
     는
    -1.24
     ricco
    -1.23
    Actually
    -1.23
    ţional
    -1.22
    ς
    -1.22
     различни
    -1.20
     навіть
    -1.20
     mediados
    -1.18
    Essentially
    -1.18
    POSITIVE LOGITS
    ↵↵
    1.64
    1
    1.52
     också
    1.48
    也会
    1.46
    也将
    1.38
     tiež
    1.37
     MÉXICO
    1.37
     laboratories
    1.32
    Unisex
    1.30
    0
    1.28
    Activations Density 0.047%

    No Known Activations