© 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. 70333
    Prev
    Next
    INDEX
    Explanations

    mechanism, action, and effects

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

    words and phrases related to drug mechanisms of action and pharmacological effects in scientific contexts.

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

    The neuron detects specialized pharmacological and biochemical action vocabulary—i.e. technical terms describing mechanisms of drug or toxin effects (binding, inhibition, induction, activity, 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_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
     Пара
    -0.81
    menso
    -0.80
    cies
    -0.78
    ginx
    -0.77
    rative
    -0.75
    নি
    -0.75
     contraceptives
    -0.73
    signOut
    -0.73
    häng
    -0.72
     miasta
    -0.71
    POSITIVE LOGITS
     action
    2.11
     actions
    1.85
     mechanism
    1.73
     target
    1.71
     acting
    1.65
     targets
    1.65
     effects
    1.59
     mechanisms
    1.51
     mode
    1.51
    mechanism
    1.36
    Activations Density 0.416%

    No Known Activations