© 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. 75484
    Prev
    Next
    INDEX
    Explanations

    license and copyright notices

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

    The neuron strongly responds to the “>” character marking the end of a markup tag.

    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
    ).
    -3.70
    );
    -3.41
    1
    -3.09
    In
    -3.08
    Now
    -2.92
    2
    -2.81
    replyreport
    -2.81
    ”;
    -2.67
    Before
    -2.63
     щодо
    -2.59
    POSITIVE LOGITS
    苤
    3.42
    缯
    2.94
    圌
    2.77
    ܆
    2.72
     apresent
    2.72
     rivales
    2.70
     echte
    2.70
    
    2.69
     lidí
    2.66
    
    2.64
    Activations Density 0.001%

    No Known Activations