Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 1991
    Prev
    Next
    INDEX
    Explanations

    This neuron identifies mentions of pulmonary symptoms—especially dyspnea and different types of cough.

    oai_token-act-pair · o4-miniTriggered by @drejcpesjakpesjak

    The neuron detects mentions of clinical symptoms and symptom-describing phrases in medical text, especially respiratory symptoms and related clinical descriptors.

    oai_token-act-pair · gpt-5-miniTriggered by @drejcpesjakpesjak
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    1.21
    ঞ্জের
    0.80
    🚫
    0.79
    MQTT
    0.79
    <unused2197>
    0.76
    Serialization
    0.75
    🔄
    0.74
    Preprocessing
    0.74
    섣
    0.74
    🌐
    0.74
    POSITIVE LOGITS
     阅读全文
    2.19
    </h1>
    2.06
    </h2>
    2.05
    </h3>
    1.97
     [...]
    1.91
     \...
    1.82
     […]
    1.82
    </blockquote>
    1.78
    </td>
    1.65
     \\
    1.62
    Activations Density 7.485%

    No Known Activations