© 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. 50022
    Prev
    Next
    INDEX
    Explanations

    filtration and membranes

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

    technical terms and descriptions related to filtration systems and membrane technology.

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

    The neuron fires most strongly on specialized scientific terms for membrane‐based virus filtration (e.g. “polyvinylidene fluoride membrane,” “hepatitis B virus”), so it’s looking for technical membrane‐filtration and virus‐related terminology in research text.

    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
     Orte
    -0.72
     které
    -0.70
    Combat
    -0.70
    ShortName
    -0.69
     convierte
    -0.66
     curiosidad
    -0.66
     Popcorn
    -0.64
     sabiduría
    -0.63
    krist
    -0.62
    Prab
    -0.62
    POSITIVE LOGITS
     filtration
    1.73
     filters
    1.63
     filter
    1.59
    Filter
    1.54
    filter
    1.52
     Filter
    1.45
     membrane
    1.43
     Filtration
    1.42
    filtration
    1.34
     Membrane
    1.33
    Activations Density 0.065%

    No Known Activations