© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6898
    Prev
    Next
    INDEX
    Explanations

    adenocarcinoma and carcinoma

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

    medical terms related to carcinomas and adenocarcinomas.

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

    The neuron fires on mentions of malignant tumor or cancer–related terms (especially words like “carcinoma,” “adenocarcinoma,” “omas,” etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     even
    -1.47
    vají
    -1.38
    dė
    -1.37
     ragaz
    -1.37
     piese
    -1.33
     cantora
    -1.30
     atriz
    -1.28
     wako
    -1.27
     splend
    -1.27
     [];
    -1.24
    POSITIVE LOGITS
     aislados
    1.71
     vacía
    1.65
    *}[
    1.59
     desagrad
    1.59
     otras
    1.59
     encantado
    1.50
     múltiple
    1.48
     reconocidos
    1.48
     vistos
    1.47
    logique
    1.45
    Activations Density 0.236%

    No Known Activations