© 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. 2131
    Prev
    Next
    INDEX
    Explanations

    periodontal disease and infection

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

    The neuron detects dental and periodontal terminology, particularly focusing on words related to gum disease and periodontal treatment.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Modelo
    -0.71
     Burbank
    -0.65
    liked
    -0.64
    gı
    -0.62
     מא
    -0.61
    hoedd
    -0.61
    出手
    -0.60
     solvent
    -0.60
    utsches
    -0.60
    sns
    -0.59
    POSITIVE LOGITS
    doped
    0.72
    ENODE
    0.70
    Counter
    0.69
    fille
    0.68
     cyberpunk
    0.66
    ENTA
    0.66
     Personas
    0.65
    PUN
    0.65
     dandy
    0.64
     erythro
    0.64
    Activations Density 0.098%

    No Known Activations