© 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. 34-GEMMASCOPE-RES-131K
    4. 12181
    Prev
    Next
    INDEX
    Explanations

    intestinal disorders

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

    medical or health-related text discussing treatments, drugs, or therapeutic applications.

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

    The neuron responds to very common function words (stop words) such as articles, prepositions, and conjunctions.

    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
     culturel
    -0.85
     nourrir
    -0.85
     Свя
    -0.83
    вання
    -0.82
     médicament
    -0.79
     serviços
    -0.77
     chaleureux
    -0.76
     веке
    -0.76
    TB
    -0.75
     MATHEMATICS
    -0.75
    POSITIVE LOGITS
     gestos
    0.88
     فهو
    0.87
     defenses
    0.86
     allies
    0.85
     Shopping
    0.82
     Slag
    0.80
     aesthetic
    0.77
     defences
    0.76
    ございません
    0.76
     Desserts
    0.75
    Activations Density 0.030%

    No Known Activations