© 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. 10-GEMMASCOPE-RES-131K
    4. 90780
    Prev
    Next
    INDEX
    Explanations

    angiotensin papillomavirus

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

    scientific and medical terminology, particularly related to biochemistry and anatomical terms.

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

    The neuron strongly activates on fragments of “renin-angiotensin-aldosterone” system terms (e.g. the ren/ang/aldo pieces), so it’s detecting mentions of the renin-angiotensin hormone system.

    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
    栒
    -1.70
    tabolism
    -1.69
    忖
    -1.68
    睨
    -1.64
    tiembre
    -1.60
    桫
    -1.59
    !(:
    -1.58
     gött
    -1.58
     ilustraciones
    -1.57
     саны
    -1.55
    POSITIVE LOGITS
    Even
    1.90
    even
    1.64
    There
    1.59
     and
    1.53
    Ultimately
    1.52
    Hanya
    1.48
    When
    1.48
    e
    1.47
    These
    1.46
    Даже
    1.44
    Activations Density 0.577%

    No Known Activations