© 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. 38782
    Prev
    Next
    INDEX
    Explanations

    gastric medical conditions

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

    the word "gastric" in medical contexts.

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

    The neuron fires on tokens beginning with the letter sequence "ga," such as "Gale" and "gastric."

    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
    -4.34
    ↵↵
    -3.28
    5
    -2.95
     umgangssprach
    -2.81
        
    -2.77
    他
    -2.70
     beinahe
    -2.66
    偶然
    -2.66
    та
    -2.55
     Notably
    -2.50
    POSITIVE LOGITS
    ⑊
    3.08
     knows
    2.91
    zzlement
    2.78
    襌
    2.67
    ﺐ
    2.61
    沵
    2.56
    鹮
    2.55
     maestros
    2.55
    鬭
    2.53
    这样一个
    2.50
    Activations Density 0.009%

    No Known Activations