© 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. 20498
    Prev
    Next
    INDEX
    Explanations

    Zen, Zeno, and Zend

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

    The neuron strongly activates on any token containing the substring “Zen” (including variants like Zeno, Zeni, ZEN).

    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
    訁
    -2.89
    歘
    -2.84
    盦
    -2.80
    
    -2.78
     wist
    -2.77
    顚
    -2.69
    焌
    -2.67
    襌
    -2.56
    翃
    -2.56
    
    -2.53
    POSITIVE LOGITS
    We
    3.25
    There
    3.11
    All
    3.09
    Some
    2.94
    After
    2.94
    These
    2.86
    }$
    2.81
    Just
    2.72
     supremely
    2.64
    Since
    2.63
    Activations Density 0.003%

    No Known Activations