© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99327
    Prev
    Next
    INDEX
    Explanations

    programming constructs and languages

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

    The neuron fires on generic type parameters and generic‐type declarations (e.g. tokens like TKey, TEntity, DbSet<…>, SqlParameter<…>, BaseRepository<T,…>, etc.).

    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
    檍
    -2.56
    ῞
    -2.33
    鳏
    -2.30
     мы
    -2.23
    原标题
    -2.23
     strenuous
    -2.19
    宬
    -2.16
    女
    -2.13
    小结
    -2.11
     cristi
    -2.08
    POSITIVE LOGITS
    2
    2.61
    {
    2.61
    ان
    2.41
    2.27
    .
    2.20
    In
    2.19
    1
    2.16
    er
    2.14
    在
    2.14
    他
    2.13
    Activations Density 0.001%

    No Known Activations