© 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. 9952
    Prev
    Next
    INDEX
    Explanations

    labs and laboratories

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

    laboratory-related terms (Lab, Laboratory) in scientific or technical contexts.

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

    This neuron detects mentions of laboratories (the token “lab” or its language variants like “laboratorio,” “laboratoire,” etc.) in organization or place names.

    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
     zustand
    -1.63
     utilisez
    -1.63
     ajoutez
    -1.53
     sportiva
    -1.51
     transférez
    -1.51
     pensez
    -1.49
     doppia
    -1.49
     leggera
    -1.48
    Nevertheless
    -1.48
     sabbia
    -1.48
    POSITIVE LOGITS
     in
    2.19
     of
    1.77
     –
    1.70
    d
    1.52
     Labs
    1.49
     —
    1.48
     }^{
    1.40
     }^{*}
    1.34
    了个
    1.34
     [
    1.31
    Activations Density 0.036%

    No Known Activations