© 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. 34-GEMMASCOPE-RES-131K
    7. 47637
    Prev
    Next
    INDEX
    Explanations

    Cancer Society

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

    references to the American Cancer Society.

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

    The neuron detects mentions of “Cancer Society” organization names (e.g. American Cancer Society, Canadian Cancer Society).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     мой
    -0.70
    isca
    -0.68
    ‹
    -0.67
    Vest
    -0.66
    ใหม่
    -0.65
    ©
    -0.65
    SpringBootTest
    -0.65
    stasia
    -0.64
    проек
    -0.64
    baric
    -0.64
    POSITIVE LOGITS
     Wies
    0.77
     ఉన్న
    0.76
    螈
    0.75
     budgetary
    0.74
     neb
    0.71
    nasio
    0.71
    겪
    0.69
     preju
    0.69
     courthouse
    0.69
    genza
    0.69
    Activations Density 0.065%

    No Known Activations