© 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. 75238
    Prev
    Next
    INDEX
    Explanations

    comment indicators like "comment"

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

    The neuron detects comment‐count headings (the “Comments” label and its associated number) in the interface.

    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
     garantir
    -2.05
    傀
    -2.02
    ilirsiniz
    -1.90
    匍
    -1.88
     насос
    -1.83
     необходимо
    -1.81
     Addressing
    -1.79
    ALREADY
    -1.78
     fomentar
    -1.77
     Ayrıca
    -1.77
    POSITIVE LOGITS
    ⦊
    1.87
    뺀
    1.86
     продолжает
    1.85
     guangdong
    1.83
    ating
    1.79
    ar
    1.77
     потім
    1.75
    ergies
    1.73
    ant
    1.73
            
    1.69
    Activations Density 0.053%

    No Known Activations