© 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. 70817
    Prev
    Next
    INDEX
    Explanations

    code snippets

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

    The neuron fires on numeric literals (integers and decimals) in the code.

    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
    l
    -2.52
    );
    -2.03
     \
    -1.98
    <em>
    -1.95
    ];
    -1.88
    ↵↵
    -1.87
    \_
    -1.86
    </h2>
    -1.82
    ↵
    -1.80
    m
    -1.77
    POSITIVE LOGITS
    
    2.00
    aimana
    1.93
     savior
    1.90
    퐶
    1.90
    
    1.88
    ของ
    1.84
    túi
    1.84
    ༈
    1.83
    甴
    1.79
     they
    1.77
    Activations Density 0.010%

    No Known Activations