© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28601
    Prev
    Next
    INDEX
    Explanations

    sulfur compounds and chemistry

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

    words related to sulfur and sulfur compounds in scientific and chemical contexts.

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

    The neuron specifically fires on mentions of sulfur or sulfur‐containing chemical species.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     ตอน
    -2.06
    
    -1.95
    
    -1.91
    
    -1.88
    ﮟ
    -1.88
    horabuena
    -1.84
    鵟
    -1.81
    鉝
    -1.79
    毉
    -1.79
    が表示
    -1.79
    POSITIVE LOGITS
    \
    2.11
    }$
    2.06
    ]
    2.05
    </h1>
    2.02
    </h5>
    2.00
    та
    1.95
    ди
    1.91
    秾
    1.85
    дите
    1.84
    </td>
    1.72
    Activations Density 0.031%

    No Known Activations