© 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. 22-GEMMASCOPE-RES-131K
    7. 130902
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on generic collection type names (e.g. List<…>, Map<…>) in code.

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

    list and ArrayList declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    utusan
    -1.43
     why
    -1.38
    分かります
    -1.33
     continuó
    -1.31
     because
    -1.23
     menikmati
    -1.20
     gelangt
    -1.18
    任何
    -1.16
     Slovensku
    -1.16
     who
    -1.14
    POSITIVE LOGITS
     of
    1.45
     umid
    1.17
    蘑菇
    1.16
    -
    1.15
     vaqueros
    1.13
     brune
    1.11
    というわけで
    1.10
     dacia
    1.09
     rigide
    1.09
     面包
    1.09
    Activations Density 0.002%

    No Known Activations