© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71900
    Prev
    Next
    INDEX
    Explanations

    biological/medical conditions and outcomes

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

    scientific terms related to biological functions, effects, and activities in medical and research contexts.

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

    The neuron fires on technical, domain‐specific nouns—especially longer, often pluralized terms describing genes, interactions, cells, effects, policies, costs, activities, scans, etc.

    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
     of
    -1.83
     or
    -1.29
     and
    -1.22
    はなく
    -1.03
    with
    -0.99
    icor
    -0.99
     avec
    -0.98
    toral
    -0.97
    agles
    -0.96
    gean
    -0.96
    POSITIVE LOGITS
    Сообщение
    1.20
    soby
    1.16
    夘
    1.10
    tengo
    1.03
    Santos
    1.03
    ادم
    1.02
     campesinos
    1.02
    Gestion
    1.00
    Наталья
    1.00
    Liet
    0.99
    Activations Density 0.200%

    No Known Activations