© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2729
    Prev
    Next
    INDEX
    Explanations

    laboratory, lab, laboratories

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

    references to laboratories or lab settings in scientific or academic contexts.

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

    This neuron detects mentions of research laboratories or institutional lab locations (e.g. “Laboratori …,” “laboratory,” “laboratories,” “at,” “in”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    リュー
    -0.84
     színes
    -0.83
    ssystem
    -0.82
    bahn
    -0.81
    ypeł
    -0.80
     système
    -0.79
    обу
    -0.79
    PageData
    -0.76
     escalera
    -0.75
     zake
    -0.74
    POSITIVE LOGITS
     laboratory
    4.66
     lab
    4.03
     laboratories
    3.64
     labs
    3.31
     Laboratory
    3.31
    laboratory
    3.14
     лабора
    3.13
     laboratorio
    3.11
    Laboratory
    2.94
    实验室
    2.84
    Activations Density 0.076%

    No Known Activations