© 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. 59369
    Prev
    Next
    INDEX
    Explanations

    diseases and conditions

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

    Latin names of parasites and pathogens that cause diseases.

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

    The neuron fires on Latin binomial or parasitology terms—that is, scientific species names (and related disease names ending in –iasis).

    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
     details
    -0.84
     vzduchu
    -0.78
    inoc
    -0.76
    pulse
    -0.76
    锡
    -0.75
    HNO
    -0.75
    chauung
    -0.73
    selin
    -0.73
    DAA
    -0.73
    廬
    -0.72
    POSITIVE LOGITS
    iosis
    1.14
    mosis
    1.03
    osis
    0.87
    cosis
    0.76
    ૩
    0.76
    জন
    0.74
    ?,?,
    0.73
    tosis
    0.72
     हमारे
    0.71
     infestation
    0.70
    Activations Density 0.141%

    No Known Activations