© 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. 7654
    Prev
    Next
    INDEX
    Explanations

    hepatocellular carcinoma

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

    The neuron detects medical acronyms, especially HCC (hepatocellular carcinoma) and other medical treatment or diagnostic terms.

    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_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
    ～～～～
    -2.72
    齶
    -2.67
    哏
    -2.66
    自己是
    -2.64
    ～～
    -2.61
    謄
    -2.58
    嘬
    -2.58
    渽
    -2.53
    轳
    -2.48
    鋇
    -2.47
    POSITIVE LOGITS
    </h3>
    4.72
    {
    4.41
    ’
    3.77
    </strong>
    3.63
     ‘
    3.17
     we
    2.92
     .
    2.84
    .’
    2.83
    ’,
    2.75
    ,’
    2.64
    Activations Density 0.040%

    No Known Activations