© 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. 113476
    Prev
    Next
    INDEX
    Explanations

    blood sugar levels and control

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

    mentions of blood sugar levels and related medical terminology.

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

    The neuron activates on numeric values (measurements, quantities, and other numbers) 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
    It
    -3.42
    There
    -2.48
    You
    -2.30
    If
    -2.22
     —
    -2.17
    Even
    -2.06
    ка
    -2.05
    All
    -2.03
    Though
    -2.00
    Almost
    -2.00
    POSITIVE LOGITS
    archiwizowane
    2.11
    厛
    2.09
    鹋
    2.08
    
    1.99
    qxd
    1.99
    槼
    1.97
     může
    1.96
     wichtigsten
    1.96
     우리
    1.91
     ſch
    1.88
    Activations Density 0.002%

    No Known Activations