© 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. 10-GEMMASCOPE-RES-131K
    7. 84407
    Prev
    Next
    INDEX
    Explanations

    apolipoprotein E, epoch time

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

    proteins and genes in scientific text, particularly focusing on ApoE (Apolipoprotein E) in biomedical research papers.

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

    The neuron is selectively detecting mentions of the “E” allele or isoform of apolipoprotein (Apo E) in gene‐ or protein‐name contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     ſou
    -1.77
    ſy
    -1.52
    ffiche
    -1.47
    ⭕
    -1.45
     robuste
    -1.45
    )»
    -1.41
    ссора
    -1.40
    juga
    -1.40
     ("%
    -1.39
    >=</
    -1.37
    POSITIVE LOGITS
    了很多
    1.44
    </b>
    1.43
    !
    1.41
     have
    1.41
     spezielle
    1.38
      
    1.32
     further
    1.30
     others
    1.30
     Türen
    1.30
     even
    1.29
    Activations Density 0.122%

    No Known Activations