© 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. 34-GEMMASCOPE-RES-131K
    7. 107965
    Prev
    Next
    INDEX
    Explanations

    neurotransmitters and biomolecules

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

    chemical compounds and neurotransmitters in scientific text, particularly abbreviated chemical names.

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

    The neuron is picking out numerical measurement tokens and concentration or dosage values (i.e. numbers and units).

    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
     douane
    -0.81
    jonas
    -0.76
     والح
    -0.70
    
    -0.70
    ską
    -0.70
     каким
    -0.69
    żu
    -0.68
     anlaş
    -0.68
    bev
    -0.68
    PRD
    -0.68
    POSITIVE LOGITS
     serotonin
    1.09
     adrenaline
    1.06
     acetylcholine
    0.98
     histamine
    0.97
     brady
    0.93
     dopamine
    0.85
     nore
    0.84
    nore
    0.81
     caffeine
    0.77
    ایل
    0.76
    Activations Density 0.554%

    No Known Activations