© 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. 22-GEMMASCOPE-RES-131K
    4. 68950
    Prev
    Next
    INDEX
    Explanations

    find searching occurrences

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

    The neuron activates on programming identifiers and keywords for search‐type operations (e.g. find, search, indexOf, binary_search, lower_bound).

    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
    ΐ
    -1.05
    resizingMask
    -1.03
     conceptos
    -1.00
     about
    -0.97
     regalías
    -0.97
     黄色
    -0.96
     Chapitre
    -0.95
    Livraison
    -0.95
     Danh
    -0.94
     ένα
    -0.94
    POSITIVE LOGITS
     find
    1.34
     search
    1.33
     searches
    1.16
     tìm
    1.16
     found
    1.16
     Search
    1.14
     searching
    1.13
     searched
    1.06
     hope
    1.04
     distance
    1.02
    Activations Density 0.020%

    No Known Activations