© 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. 22-GEMMASCOPE-RES-131K
    7. 36065
    Prev
    Next
    INDEX
    Explanations

    commentary and explanations

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

    The neuron detects mentions of extra or supplementary material—words signaling commentary, introductions, notes, tips, or other editorial content.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    闺蜜
    -0.97
    各式
    -0.96
    見ると
    -0.94
    '
    -0.92
     cambian
    -0.92
     many
    -0.91
    مزید
    -0.90
     recently
    -0.90
     escalated
    -0.89
    嘉宾
    -0.87
    POSITIVE LOGITS
     why
    1.47
     about
    1.43
     explanation
    1.29
     how
    1.20
     explanations
    1.10
     written
    1.09
     explain
    1.08
     explains
    1.08
    crizione
    1.05
     erklä
    1.03
    Activations Density 0.072%

    No Known Activations