© 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. 104229
    Prev
    Next
    INDEX
    Explanations

    map, hash, dictionary

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

    the keyword "map" or "Map" in programming code, especially in data structure declarations and imports.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on occurrences of the identifier “map” (and related variants like “unordered_map” or “Map”) when referring to map/dictionary types in code.

    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
    晔
    -1.63
    hynch
    -1.55
     längere
    -1.51
     rhino
    -1.48
     что
    -1.48
    álva
    -1.45
     nếu
    -1.44
     einzigartige
    -1.43
    uffe
    -1.42
    aziland
    -1.41
    POSITIVE LOGITS
    \
    1.77
     kopf
    1.48
    )$
    1.48
    ?」
    1.45
     kaas
    1.45
     Songtext
    1.45
     tisch
    1.45
     deutschland
    1.44
     copia
    1.41
    內的
    1.39
    Activations Density 0.040%

    No Known Activations