© 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. 50420
    Prev
    Next
    INDEX
    Explanations

    liver disease, function, and transplant

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

    references to the liver in medical and scientific contexts.

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

    The neuron strongly activates on mentions of “liver” (and its medical roots like “hepat‐”), i.e. terms referring to the liver.

    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
    “
    -0.86
     įva
    -0.83
    jectives
    -0.81
     väg
    -0.79
     juos
    -0.76
     кожи
    -0.75
     Extensive
    -0.75
     gegeben
    -0.75
    ourcen
    -0.74
    риях
    -0.74
    POSITIVE LOGITS
    wurst
    1.21
     enzymes
    0.93
     cirrhosis
    0.92
     transplant
    0.89
     glycogen
    0.84
    hant
    0.84
    kjø
    0.82
     disesuaikan
    0.79
    幟
    0.79
    lierten
    0.78
    Activations Density 0.048%

    No Known Activations