© 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. 28529
    Prev
    Next
    INDEX
    Explanations

    section headers or labels

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

    This neuron detects JavaScript callback syntax, especially jQuery’s `.each` calls and inline `function(…)` parameter lists.

    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
     when
    -1.83
     that
    -1.34
     if
    -1.31
     while
    -1.25
     because
    -1.23
     despite
    -1.19
     during
    -1.17
    市長
    -1.17
     without
    -1.16
     both
    -1.09
    POSITIVE LOGITS
     (!__
    1.33
     dessa
    1.16
    anlagen
    1.07
     sviluppo
    1.06
     bascul
    1.05
    随着
    1.05
     Bíblia
    1.05
     créer
    1.02
    ͛
    1.02
     trám
    1.01
    Activations Density 0.000%

    No Known Activations