© 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. 90364
    Prev
    Next
    INDEX
    Explanations

    parental controls permission rights guidance

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

    The neuron is strongly activated by occurrences of the word “parental.”

    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
    锒
    -3.23
    鷙
    -2.94
    渽
    -2.88
    喼
    -2.70
    鐃
    -2.67
    涐
    -2.66
     Abstr
    -2.64
     лютого
    -2.64
    iettes
    -2.55
    浯
    -2.55
    POSITIVE LOGITS
     
    3.42
    9
    3.36
    2
    3.28
     "
    3.22
    ࿚
    3.17
    めっちゃ
    3.16
    8
    3.11
    This
    3.11
    7
    3.03
    めちゃ
    3.00
    Activations Density 0.002%

    No Known Activations