© 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. 90333
    Prev
    Next
    INDEX
    Explanations

    code structure identifiers

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

    The neuron fires on code identifiers for collection‐type data structures (e.g. list, tuple, map, cache).

    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
    ﺶ
    -1.98
    ֟
    -1.89
     capitolo
    -1.88
    )?
    -1.88
    日に
    -1.88
     satisfecho
    -1.86
     habido
    -1.82
    齮
    -1.82
     inteligen
    -1.80
     webu
    -1.80
    POSITIVE LOGITS
    f
    2.09
    "
    1.98
    :
    1.88
    铪
    1.87
    fl
    1.83
    {\
    1.81
     —
    1.79
     –
    1.78
     пять
    1.75
    „
    1.73
    Activations Density 0.010%

    No Known Activations