© 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. 20397
    Prev
    Next
    INDEX
    Explanations

    senior citizens and doctors

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

    The neuron strongly activates on medical or health–related terminology (e.g. “senior citizens,” “medical doctor,” “pulmonic”).

    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
    ༑
    -1.44
    3
    -1.41
    }
    -1.41
    ğin
    -1.40
    Magento
    -1.38
     ſtate
    -1.38
    lässt
    -1.38
     pleaſure
    -1.36
    스
    -1.35
    那些
    -1.34
    POSITIVE LOGITS
     only
    1.84
     where
    1.51
     needs
    1.50
    何故
    1.38
     as
    1.34
     even
    1.33
     eventually
    1.32
     there
    1.31
     first
    1.30
    there
    1.27
    Activations Density 0.088%

    No Known Activations