© 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. 11324
    Prev
    Next
    INDEX
    Explanations

    high authority titles

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

    The neuron fires on high‐level formal titles or leadership ranks—e.g. tokens like “General,” “Chief,” “Supreme,” or “Directorate” in organizational names.

    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
     extremamente
    -1.67
    adapted
    -1.59
    ྄
    -1.52
     など
    -1.48
     wła
    -1.45
     occasional
    -1.43
                
    -1.42
                   
    -1.41
     creciente
    -1.41
               
    -1.41
    POSITIVE LOGITS
    Тема
    1.62
    Having
    1.51
    Shortly
    1.50
    Some
    1.42
    שלום
    1.39
     cordones
    1.38
    er
    1.38
    Very
    1.37
    There
    1.36
     bardak
    1.35
    Activations Density 0.076%

    No Known Activations