© 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. 10-GEMMASCOPE-RES-131K
    7. 102287
    Prev
    Next
    INDEX
    Explanations

    medication use

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

    the word "medication" in medical and healthcare contexts.

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

    The neuron strongly activates whenever the exact word “medication” appears.

    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
    衚
    -2.75
    In
    -2.53
    荩
    -2.52
    síða
    -2.42
    。。
    -2.39
    ．．
    -2.38
     تاکید
    -2.36
    欵
    -2.33
    大幅
    -2.17
     musik
    -2.16
    POSITIVE LOGITS
    .
    3.09
    the
    2.81
     природа
    2.41
    玧
    2.25
    a
    2.25
     ופ
    2.23
    行って
    2.22
     suporta
    2.19
     we
    2.17
     コス
    2.17
    Activations Density 0.004%

    No Known Activations