© 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. 76322
    Prev
    Next
    INDEX
    Explanations

    oral health recall

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

    terminology and content related to dental health, including words like "dental," "oral health," "caries," and other dental-related terms.

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

    The neuron strongly activates on specialized dental‐health terminology (e.g. “dental,” “oral,” “caries,” “care,” “service”) and is thus detecting dentistry-related content.

    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
     dyn
    -0.87
     médica
    -0.81
     clinic
    -0.79
     clínica
    -0.74
     clinics
    -0.74
     outpatient
    -0.73
     reader
    -0.69
     dentist
    -0.68
     dentistry
    -0.66
     feathers
    -0.66
    POSITIVE LOGITS
     recall
    1.05
    த
    0.76
     Recall
    0.75
     recalls
    0.75
     rustling
    0.74
    urlar
    0.74
     recalled
    0.73
     indices
    0.73
    дя
    0.71
    hode
    0.71
    Activations Density 0.066%

    No Known Activations