© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 61078
    Prev
    Next
    INDEX
    Explanations

    accessing list elements

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

    The neuron strongly activates on code snippets where values are being accessed (via bracket‐indexing or dot‐property access) and then compared or tested for membership (e.g. ==, ===, “not in,” 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
     only
    -1.40
     it
    -1.36
    maksi
    -1.30
     not
    -1.25
     all
    -1.19
    了两
    -1.16
     two
    -1.16
     just
    -1.15
     alleen
    -1.13
     який
    -1.10
    POSITIVE LOGITS
     distintas
    1.42
    different
    1.39
    比较好
    1.34
     different
    1.33
     distintos
    1.32
    
    1.27
    änning
    1.27
     различных
    1.25
    various
    1.24
     jeweiligen
    1.23
    Activations Density 0.035%

    No Known Activations