© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 12149
    Prev
    Next
    INDEX
    Explanations

    Chon, Chong, Chom, chond words

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

    The neuron is tuned to detect Greek/Latin-derived biomedical roots—especially the “chondr/ond” sequence—in specialized scientific or medical terms.

    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
    Globe
    -0.69
     begeistert
    -0.67
    用例
    -0.67
     Wife
    -0.66
    ophen
    -0.66
    docs
    -0.66
     József
    -0.66
    对话框
    -0.65
     vergessen
    -0.65
     میلیارد
    -0.65
    POSITIVE LOGITS
     ihre
    0.71
    нцип
    0.71
     zás
    0.71
    nath
    0.71
     Neuf
    0.70
    acky
    0.70
     CONS
    0.69
    uestas
    0.69
    ष्
    0.69
    以上に
    0.68
    Activations Density 0.022%

    No Known Activations