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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77404
    Prev
    Next
    INDEX
    Explanations

    toothpaste and brushing

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

    dental health and oral care related terms, particularly involving toothpaste, fluoride, and tooth treatments.

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

    The neuron is highly sensitive to numeric and quantitative expressions (numbers, measurements, units, group labels) in scientific or technical text.

    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
     Landmark
    -0.72
    udio
    -0.70
    dismo
    -0.70
    vorm
    -0.68
    acro
    -0.68
    vern
    -0.67
     LXX
    -0.67
     Macedonian
    -0.66
     Invoke
    -0.66
     glabrous
    -0.66
    POSITIVE LOGITS
     toothbrush
    2.06
     toothpaste
    1.94
     brush
    1.23
     Tooth
    1.20
     brushing
    1.17
     bristles
    1.13
     tooth
    1.09
    Tooth
    1.03
     зуб
    1.00
     fluoride
    0.96
    Activations Density 0.016%

    No Known Activations