© 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. 109212
    Prev
    Next
    INDEX
    Explanations

    NF-kappa B

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

    The neuron detects mentions of NF-kappa B and related molecular signaling pathways in scientific and medical texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     motore
    -0.77
     %),
    -0.76
     conosce
    -0.75
    equalsIgnoreCase
    -0.72
    醫
    -0.71
     collapsed
    -0.69
     Ptole
    -0.69
    áni
    -0.69
     угле
    -0.68
     tsu
    -0.67
    POSITIVE LOGITS
     NF
    1.89
    NF
    1.47
     Rel
    1.27
    nf
    1.17
     nf
    1.11
     Ik
    1.07
    Rel
    1.02
     TNF
    1.00
     REL
    0.93
     nuclear
    0.92
    Activations Density 0.095%

    No Known Activations