© 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. 109411
    Prev
    Next
    INDEX
    Explanations

    MAPK ERK JNK activation

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

    cellular signaling pathway components, particularly MAP kinase (MAPK) and ERK signaling molecules in biochemical pathways.

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

    This neuron identifies mentions of protein kinases with letter + number names (for example “JNK” or “p38”).

    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
    赳
    -0.78
    yesi
    -0.69
     Pellegrini
    -0.68
     Pelleg
    -0.68
     else
    -0.67
    Modo
    -0.66
    Sense
    -0.66
     klä
    -0.65
     confirmation
    -0.64
    elems
    -0.64
    POSITIVE LOGITS
     ERK
    1.17
     Raf
    0.93
     MAP
    0.91
     JN
    0.85
    ERK
    0.84
     radium
    0.81
     ME
    0.81
     RAF
    0.79
     splint
    0.79
     xiao
    0.78
    Activations Density 0.118%

    No Known Activations