© 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. 65225
    Prev
    Next
    INDEX
    Explanations

    pharmacological actions, effects, and activity

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

    The neuron identifies terms related to pharmacology and medicine, particularly focusing on words like "pharmacological," "pharmacology," and related scientific terminology within medical/pharmaceutical contexts.

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

    The neuron activates on specialized biomedical terminology, especially drug‐ and physiology‐related technical words (e.g. “pharmacology,” “physiological,” “pharmacological,” 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
     continúas
    -2.88
    蜮
    -2.48
     ‚
    -2.39
    呦
    -2.34
    </i>
    -2.33
     Including
    -2.23
    蟜
    -2.22
    ※※
    -2.17
     The
    -2.00
     universitaria
    -2.00
    POSITIVE LOGITS
    </sup>
    3.06
    ```
    2.64
    </td>
    2.53
    }{
    2.25
    </h4>
    2.25
    ”，
    2.23
    }
    2.16
     और
    2.09
    ">
    2.08
     berbahaya
    2.06
    Activations Density 0.018%

    No Known Activations