© 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. 34-GEMMASCOPE-RES-131K
    4. 89824
    Prev
    Next
    INDEX
    Explanations

    carbon monoxide and carbon dioxide

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

    references to carbon monoxide and its chemical symbol CO in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Caching
    -1.02
    caching
    -0.84
    CacheManager
    -0.75
    빅
    -0.74
    Ṛ
    -0.73
    Cache
    -0.73
     Mojave
    -0.70
    voet
    -0.70
    caches
    -0.70
    publique
    -0.69
    POSITIVE LOGITS
     CO
    3.66
     carbon
    2.95
    CO
    2.92
     Carbon
    2.61
    Carbon
    2.34
    carbon
    2.31
     monoxide
    2.28
     CARBON
    2.02
    CARBON
    1.77
     karbon
    1.75
    Activations Density 0.080%

    No Known Activations