© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99097
    Prev
    Next
    INDEX
    Explanations

    Map and Set operations

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

    The neuron strongly activates on TypeScript‐style generic type syntax—particularly angle brackets, colons, and “Set<…>” declarations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    JavaScript/TypeScript code that uses ES6 collection data structures and operations, particularly creating, iterating, and mutating sets/maps.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    references to Set and Map data structures in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
     Psychologie
    -0.92
     Chhattisgarh
    -0.83
    ♠
    -0.82
    riding
    -0.80
    JO
    -0.79
    と一緒に
    -0.78
     غزة
    -0.78
     センター
    -0.77
    ᐱ
    -0.77
    тельным
    -0.74
    POSITIVE LOGITS
     Map
    1.08
     deleting
    0.86
    Map
    0.77
     MAP
    0.77
    MapView
    0.77
     maple
    0.74
     has
    0.74
    Nab
    0.73
     Maps
    0.73
    Reflect
    0.72
    Activations Density 0.017%

    No Known Activations