© 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. 104161
    Prev
    Next
    INDEX
    Explanations

    leprosy

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

    words and terms related to leprosy and other infectious diseases.

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

    This neuron detects occurrences of leprosy and its related scientific terms (e.g., Mycobacterium leprae, bacillary leprosy).

    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
     scintill
    -1.95
    ペース
    -1.94
    いかない
    -1.88
     We
    -1.75
    さまで
    -1.73
    餵
    -1.73
     \
    -1.66
    ドキ
    -1.66
    そうですね
    -1.66
    個人的には
    -1.64
    POSITIVE LOGITS
     nuova
    2.05
    毉
    1.95
     nuovo
    1.94
     });
    
    1.82
    ᩠
    1.80
    !!!!
    1.79
    さんも
    1.79
    ??
    1.78
     dipin
    1.77
     seluruh
    1.76
    Activations Density 0.021%

    No Known Activations