© 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. 34-GEMMASCOPE-RES-131K
    7. 60107
    Prev
    Next
    INDEX
    Explanations

    asbestos or common question/list starters

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

    The neuron is strongly triggered by technical mentions of asbestos exposure and asbestos‐related lung disease (e.g. asbestos, asbestos‐related lung disease, pleural mesothelioma).

    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
    lasma
    -0.90
     任
    -0.83
    ocarpus
    -0.79
    cuentes
    -0.78
     рэ
    -0.77
    sterone
    -0.75
     Seel
    -0.74
    cipline
    -0.74
     extrema
    -0.73
    inematics
    -0.72
    POSITIVE LOGITS
     asbestos
    2.41
     Asbestos
    1.90
     fibers
    1.47
     fibres
    1.39
    bestos
    1.36
     fiber
    1.35
     chrys
    1.35
     Fibers
    1.27
    fiber
    1.23
     fibre
    1.20
    Activations Density 0.025%

    No Known Activations