© 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. 117283
    Prev
    Next
    INDEX
    Explanations

    extracts antimalarial anticancer inhibitory activities

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

    scientific literature citations and references, particularly in academic papers about medical or chemical research.

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

    This neuron fires on domain‐specific activity terms describing a compound’s biological or therapeutic actions (e.g. anticancer, anthelmintic, antimalarial, radical scavenger).

    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
    Ἡ
    -0.87
    ICLE
    -0.81
     phosphorus
    -0.78
    Cevapla
    -0.77
    سل
    -0.77
    畵
    -0.75
     nehme
    -0.73
     الوح
    -0.73
     ammonia
    -0.72
    GeneratedMessage
    -0.71
    POSITIVE LOGITS
     Extracts
    0.96
     extracts
    0.95
     extract
    0.92
    шње
    0.90
     scavenging
    0.88
     inhibitory
    0.85
     HPLC
    0.85
    Abuja
    0.84
     against
    0.83
    assay
    0.81
    Activations Density 0.028%

    No Known Activations