© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42282
    Prev
    Next
    INDEX
    Explanations

    MAPK pathway activation

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

    protein kinase signaling pathways, particularly MAP kinases in cellular signaling cascades.

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

    The neuron strongly activates on mentions of MAP kinase (MAPK) pathway components (e.g. “MAPK,” “mitogen-activated protein kinase,” “MEK,” “ERK,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </b>
    -1.66
     ",
    -1.56
     the
    -1.55
    </strong>
    -1.54
    though
    -1.51
    "].
    -1.50
     oppure
    -1.43
    </h4>
    -1.40
    几个人
    -1.38
    even
    -1.37
    POSITIVE LOGITS
    觧
    1.74
    乆
    1.50
    だそうです
    1.47
    мии
    1.44
    HDF
    1.41
     musí
    1.37
    微博
    1.37
     conocida
    1.34
    রণ
    1.32
     maravillosa
    1.31
    Activations Density 0.064%

    No Known Activations