© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59550
    Prev
    Next
    INDEX
    Explanations

    medication and drug names

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

    names of pharmaceutical drugs and chemical compounds.

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

    This neuron detects complex chemical or pharmaceutical compound names.

    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
     from
    -0.75
     partai
    -0.75
     футболка
    -0.74
    PLEX
    -0.70
    arro
    -0.70
     sostanza
    -0.70
     ditangkap
    -0.69
    factura
    -0.68
    sero
    -0.67
     well
    -0.66
    POSITIVE LOGITS
    vimos
    1.02
     tos
    0.91
     doña
    0.88
    プレイヤー
    0.88
    tehen
    0.87
     Penguins
    0.84
    INION
    0.82
    TODAY
    0.81
    PACKET
    0.80
     disseminated
    0.80
    Activations Density 0.148%

    No Known Activations