© 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. 34-GEMMASCOPE-RES-131K
    4. 60677
    Prev
    Next
    INDEX
    Explanations

    Elasticsearch, Solr, search, indexing

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

    The neuron is detecting programming‐language code tokens (e.g. class names, keywords, punctuation) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     dairy
    -0.81
    AVER
    -0.75
    vscode
    -0.74
     foaming
    -0.68
    GraphicsUnit
    -0.68
     Ка
    -0.67
    ographical
    -0.66
    èvre
    -0.66
    𝔡
    -0.65
     male
    -0.65
    POSITIVE LOGITS
    lucene
    1.56
     search
    1.54
     Elasticsearch
    1.45
    Luc
    1.44
     indexing
    1.42
    elasticsearch
    1.37
    Elastic
    1.35
     Elastic
    1.35
    search
    1.34
     Luc
    1.33
    Activations Density 0.149%

    No Known Activations