© 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. 105904
    Prev
    Next
    INDEX
    Explanations

    code namespaces

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

    This neuron detects PHP fully qualified class or namespace references, i.e. the backslash separators used in PHP FQCNs.

    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
    '
    -1.83
     adesivo
    -1.76
    ಱ
    -1.67
     iniziale
    -1.66
    ྂ
    -1.66
    了很多
    -1.64
    Ꮘ
    -1.63
    婓
    -1.63
    kurtka
    -1.63
     funcionam
    -1.63
    POSITIVE LOGITS
     from
    2.09
     of
    1.88
    ).
    1.78
     /
    1.76
     However
    1.62
    from
    1.57
     от
    1.53
    e
    1.53
    ↵
    1.49
     dari
    1.49
    Activations Density 0.006%

    No Known Activations