© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13530
    Prev
    Next
    INDEX
    Explanations

    cancer and disease diagnosis

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

    content about people with cancer or serious medical conditions.

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

    The neuron detects mentions of serious illnesses, especially cancer and related disease terms.

    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
    [
    -1.00
    冷漠
    -0.99
     czemu
    -0.98
    va
    -0.93
    R
    -0.93
    へ
    -0.92
    f
    -0.91
    U
    -0.89
     behavior
    -0.88
    un
    -0.88
    POSITIVE LOGITS
     cancer
    1.56
     diagnosis
    1.23
    Karakter
    1.18
    ༑
    1.17
     minimizar
    1.16
    Cancer
    1.12
    sej
    1.09
    unuz
    1.09
     disease
    1.08
     tecnologías
    1.08
    Activations Density 0.052%

    No Known Activations