© 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. 83820
    Prev
    Next
    INDEX
    Explanations

    patho or language therapy

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

    The neuron fires on occurrences of the “patho-” root in medical or biological terms (e.g. pathology, pathophysiology, pathogenesis).

    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
     gemeente
    -0.87
     Pintura
    -0.80
     Uncertainty
    -0.79
     Baptiste
    -0.77
     conducteur
    -0.77
     Lucinda
    -0.76
     bicic
    -0.76
     OTTO
    -0.75
     PAINTING
    -0.75
     snoring
    -0.75
    POSITIVE LOGITS
     pathological
    4.25
     pathology
    4.16
    patho
    3.89
     Patho
    3.84
    Patho
    3.78
     patho
    3.70
     Pathology
    3.39
     пато
    3.20
     pathologies
    3.02
     pathogenic
    2.98
    Activations Density 0.109%

    No Known Activations