© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44274
    Prev
    Next
    INDEX
    Explanations

    orthodontic

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

    terms related to orthodontics and dental appliances.

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

    The neuron strongly activates on specialized orthodontic and braces-related terminology (e.g. “orthodontic,” “orthodontists,” “brackets,” “bonding,” “aligners,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    is
    -1.86
    en
    -1.66
    enter
    -1.59
     fatale
    -1.56
     there
    -1.52
    ys
    -1.48
    ce
    -1.47
    一旁的
    -1.41
     suo
    -1.41
    ton
    -1.41
    POSITIVE LOGITS
    </b>
    2.55
    </i>
    2.52
     aquellos
    1.94
    ");
    1.93
    켭
    1.77
     climá
    1.76
     aquella
    1.73
     sólidos
    1.73
     orthodontic
    1.71
    푢
    1.71
    Activations Density 0.021%

    No Known Activations