© 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. 10-GEMMASCOPE-RES-131K
    7. 123644
    Prev
    Next
    INDEX
    Explanations

    hydrogen properties and uses

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

    The neuron detects references to hydrogen and related chemical compounds.

    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_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
    y
    -3.27
    '
    -3.09
    ?"
    -2.97
     ‘
    -2.94
    )
    -2.77
    en
    -2.75
    </strong>
    -2.63
    x
    -2.63
    et
    -2.48
    S
    -2.48
    POSITIVE LOGITS
    
    3.31
    趼
    3.23
    媗
    3.09
    姈
    2.92
    ୌ
    2.88
    轫
    2.80
    ｘ
    2.73
    chtenstein
    2.73
    ፨
    2.67
    瘣
    2.55
    Activations Density 0.013%

    No Known Activations