© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109774
    Prev
    Next
    INDEX
    Explanations

    dental plaque and calculus

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

    dental and oral hygiene terminology, particularly related to cleaning practices and periodontal health.

    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
     PAIN
    -0.79
    pering
    -0.78
    pain
    -0.75
     ***!
    -0.74
    feldt
    -0.74
    BITE
    -0.73
    📺
    -0.71
     caster
    -0.70
    واء
    -0.70
     practitioners
    -0.70
    POSITIVE LOGITS
     plaque
    1.22
    plaque
    0.96
     professional
    0.84
     Plaque
    0.82
     Professional
    0.81
     Cranston
    0.79
     Calculus
    0.79
     disclosing
    0.78
     cibo
    0.78
     acids
    0.78
    Activations Density 0.030%

    No Known Activations