© 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. 71848
    Prev
    Next
    INDEX
    Explanations

    carcinoma and names

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

    names of diseases and medical conditions, particularly carcinomas.

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

    The neuron is selectively detecting mentions of carcinoma or cancer-related terms in the text.

    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
    "
    -3.23
    1
    -3.11
    ↵
    -2.70
    м
    -2.61
     wichtigste
    -2.44
    -2.38
    s
    -2.30
     gleiche
    -2.30
    es
    -2.28
     \
    -2.28
    POSITIVE LOGITS
    ように
    2.56
     erfolgreichen
    2.45
    抬手
    2.42
    鹀
    2.42
    瑁
    2.36
    atá
    2.36
     offenen
    2.33
     privaten
    2.28
     primeros
    2.28
    𖣘
    2.27
    Activations Density 0.021%

    No Known Activations