© 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. 65610
    Prev
    Next
    INDEX
    Explanations

    dental health and treatments

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

    references to teeth and dental-related terms in medical and technical documents.

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

    the neuron strongly activates on terms related to teeth and dental concepts.

    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
    Script
    -0.95
     cocoon
    -0.81
     millennial
    -0.80
    rishnan
    -0.80
     Pregnant
    -0.78
     Aure
    -0.78
    त्म
    -0.76
     воды
    -0.76
    lidades
    -0.76
    phäre
    -0.75
    POSITIVE LOGITS
     whitening
    1.20
    brushes
    1.17
    borsa
    0.93
     Whitening
    0.93
    protetor
    0.93
    vyn
    0.90
     grze
    0.90
    etsy
    0.89
    shaded
    0.88
    🦷
    0.88
    Activations Density 0.011%

    No Known Activations