© 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. 118180
    Prev
    Next
    INDEX
    Explanations

    nucleus, nuclear, nuclei

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

    cell types and cellular structures in scientific texts.

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

    The neuron strongly activates on mentions of nuclei or nuclear contexts in scientific descriptions (e.g. “atomic nuclei,” “nuclear polarization,” “nuclei in cells”).

    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
     Live
    -0.84
     live
    -0.79
    |}{
    -0.76
    ात
    -0.76
    iems
    -0.72
    hagen
    -0.71
    égi
    -0.69
    鉻
    -0.69
    ตาย
    -0.68
    ライブ
    -0.67
    POSITIVE LOGITS
     nuclei
    3.11
    nuc
    2.02
     nucleus
    1.95
     Nuc
    1.85
     núcleos
    1.72
    Nuc
    1.62
    nucleus
    1.55
     nuclear
    1.38
     Nucleus
    1.38
    nuclear
    1.29
    Activations Density 0.083%

    No Known Activations