© 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. 99775
    Prev
    Next
    INDEX
    Explanations

    high blood glucose

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

    medical terms related to blood sugar and glycemic conditions.

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

    The neuron detects clinical terms containing the “gly” or “glyc” root—especially “glycemia,” “glycemic,” and related forms.

    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
     ausser
    -2.20
    等は
    -2.09
    AutoresizingMask
    -2.06
     ampla
    -2.02
    ’.
    -2.02
     температуры
    -1.93
    ⎊
    -1.93
    .’
    -1.92
    </sub>
    -1.90
    …)
    -1.90
    POSITIVE LOGITS
    0
    2.88
    ஂ
    2.09
    鱨
    2.06
    ープン
    2.00
     онъ
    1.96
    她的
    1.91
    颔
    1.79
    فایل
    1.77
    ه
    1.77
     godziny
    1.76
    Activations Density 0.016%

    No Known Activations