© 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. 10-GEMMASCOPE-RES-131K
    7. 21689
    Prev
    Next
    INDEX
    Explanations

    tumor necrosis factor alpha

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

    scientific or medical terms and specific protein/molecule names, particularly those related to tumor necrosis factor and growth factors.

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

    The neuron fires on key tokens within multiword named entities—such as company or organization names, place names, and technical or biochemical term components.

    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
    卨
    -1.54
     parachoque
    -1.48
     blanches
    -1.43
    ᜀ
    -1.42
    っちゃった
    -1.38
    っちゃう
    -1.38
    actéristi
    -1.36
     Certains
    -1.36
    caine
    -1.34
    Люби
    -1.34
    POSITIVE LOGITS
     when
    2.13
     ocurrió
    1.71
    </h4>
    1.54
     cuando
    1.53
     where
    1.49
    𝚊
    1.41
     जब
    1.37
     عندما
    1.37
    臵
    1.34
     când
    1.34
    Activations Density 0.454%

    No Known Activations