© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3471
    Prev
    Next
    INDEX
    Explanations

    prokaryotes and chromosomes

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

    This neuron detects technical cell-biology terms referring to subcellular structures and their formation (e.g., chloroplasts, membranes, proplastids, organelles).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     эмо
    0.73
     भावनाओं
    0.67
     эмоциона
    0.67
     Monmouth
    0.64
    Bobby
    0.64
    ijuana
    0.64
    Insurance
    0.63
     Emotions
    0.63
     Versicher
    0.61
    ♝
    0.61
    POSITIVE LOGITS
     organelles
    1.94
     cytoskeleton
    1.81
     cytoplasm
    1.77
     cytoplasmic
    1.70
     intercellular
    1.55
     ribosomes
    1.53
     cytosol
    1.53
     intracellular
    1.52
     subcellular
    1.48
     cell
    1.46
    Activations Density 0.187%

    No Known Activations