© 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. 72822
    Prev
    Next
    INDEX
    Explanations

    nested for loops

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

    The neuron lights up on occurrences of the “for” keyword (i.e. loop constructs).

    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
     then
    -1.45
     eficientes
    -1.35
    nių
    -1.33
     seguras
    -1.23
    then
    -1.16
    ebaran
    -1.16
    となりました
    -1.15
    лід
    -1.15
    kegiatan
    -1.15
     když
    -1.14
    POSITIVE LOGITS
     sumptuous
    1.49
     Therefore
    1.49
    ">
    1.42
     saurait
    1.38
    eight
    1.38
     gethan
    1.38
     Hence
    1.37
    ⿸
    1.36
     giebt
    1.36
    seven
    1.34
    Activations Density 0.005%

    No Known Activations