© 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. 22-GEMMASCOPE-RES-131K
    4. 66529
    Prev
    Next
    INDEX
    Explanations

    tumor progression of cancer

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

    references to tumors, cancer, and oncology-related medical concepts.

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

    The neuron specifically responds to the term “tumor” (including its hyphenated forms like “tumor-associated”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    。
    -1.52
    The
    -1.38
    We
    -1.38
     enten
    -1.28
     Choudh
    -1.25
    ⇘
    -1.24
    ꯳
    -1.23
     saia
    -1.22
    ///</
    -1.21
     ؛
    -1.21
    POSITIVE LOGITS
     cancer
    1.73
     cancers
    1.54
     of
    1.41
    tumor
    1.34
    Cancer
    1.27
    ↵
    1.25
     tumor
    1.21
     in
    1.18
    Designated
    1.16
     oncology
    1.16
    Activations Density 0.252%

    No Known Activations