© 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. 104216
    Prev
    Next
    INDEX
    Explanations

    error checking code

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

    This neuron detects programming identifiers (i.e. variable, function, type, and other symbol names) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     your
    -0.96
    your
    -0.94
     there
    -0.89
    local
    -0.88
     aim
    -0.86
     votre
    -0.86
    aim
    -0.86
    says
    -0.85
     kullan
    -0.85
    ämie
    -0.83
    POSITIVE LOGITS
     inaweza
    1.02
    =$?
    0.95
    玉石
    0.94
    牀
    0.93
    יקה
    0.91
     pueden
    0.91
     који
    0.90
    )#
    0.88
    bunya
    0.88
    viä
    0.88
    Activations Density 0.004%

    No Known Activations