© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43765
    Prev
    Next
    INDEX
    Explanations

    monitoring status or conditions

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

    The main thing this neuron does is detect the word “monitor” (in any form, e.g. “monitoring,” “monitors,” “monitor”) in technical contexts.

    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
    "
    -2.33
    ’
    -2.31
     Of
    -2.27
    end
    -2.02
     Virtually
    -1.98
     determinada
    -1.97
    iphery
    -1.94
     anointed
    -1.93
     Anyone
    -1.91
    缯
    -1.90
    POSITIVE LOGITS
    趼
    2.41
    ஂ
    2.36
    柃
    2.34
    錞
    2.19
     ASPECTS
    2.19
    怎么说
    2.14
    聍
    2.11
    
    2.08
     terjadinya
    2.08
    繙
    2.03
    Activations Density 0.021%

    No Known Activations