© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58813
    Prev
    Next
    INDEX
    Explanations

    non-small cell lung cancer

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

    This neuron detects the abbreviation "NSC" (Non-Small Cell) when used in medical or programming contexts.

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

    This neuron specifically detects the occurrence of the token “NSC,” as used in referring to non–small‐cell lung cancer codes or abbreviations.

    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
    狁
    -2.73
    ￪
    -2.69
    榦
    -2.67
    zehnten
    -2.64
    豨
    -2.63
    衕
    -2.59
     zvuky
    -2.55
     dezelve
    -2.50
    衚
    -2.50
    姤
    -2.47
    POSITIVE LOGITS
    </sup>
    2.89
    </td>
    2.83
    </h2>
    2.80
    </h6>
    2.75
    ！』
    2.61
     of
    2.61
     \\
    2.52
    $
    2.52
    但我
    2.45
     t
    2.44
    Activations Density 0.013%

    No Known Activations