© 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. 34-GEMMASCOPE-RES-131K
    7. 6698
    Prev
    Next
    INDEX
    Explanations

    Array index out of bound

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

    The neuron strongly activates on programming‐related array references (e.g. “Array”, array indices, “IndexOutOfRangeException”, 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_34/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
    centroids
    -0.76
     Soluble
    -0.73
     upor
    -0.67
     обосно
    -0.67
     luck
    -0.67
    ित
    -0.66
    zieży
    -0.66
     Duke
    -0.66
     soluble
    -0.66
    nextInt
    -0.64
    POSITIVE LOGITS
    Rank
    0.91
    Segment
    0.82
     Rank
    0.82
     segment
    0.82
    ்த்த
    0.81
     rank
    0.80
     Culver
    0.80
     RANK
    0.79
    segment
    0.77
    Preamble
    0.77
    Activations Density 0.008%

    No Known Activations