© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68872
    Prev
    Next
    INDEX
    Explanations

    code comments and documentation headers

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

    This neuron fires on numeric tokens—especially version numbers, copyright years, and other numeric values—when they appear in comments or doc-block annotations.

    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
    habited
    -1.41
    示意图
    -1.35
    	
    -1.35
    是因为
    -1.33
    两者
    -1.31
    咲き
    -1.25
    只需
    -1.23
    ต้องการ
    -1.23
    habitants
    -1.23
     nytt
    -1.23
    POSITIVE LOGITS
     and
    2.36
    ayage
    1.44
     somewhat
    1.42
    Dichlorobenzene
    1.30
    }=\
    1.27
     –
    1.27
    沵
    1.23
     leopardo
    1.22
     bambú
    1.21
     слегка
    1.21
    Activations Density 0.006%

    No Known Activations