© 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. 90509
    Prev
    Next
    INDEX
    Explanations

    programming data access and manipulation

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

    This neuron responds to PHP array-related syntax, in particular array declarations and bracket (`[]`/`[key]`) indexing.

    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
     Mulai
    -0.82
     aktar
    -0.82
     réjou
    -0.82
    choose
    -0.79
     rafraî
    -0.79
    Ār
    -0.77
    杼
    -0.77
    ことが多い
    -0.76
    鏷
    -0.75
    üyük
    -0.75
    POSITIVE LOGITS
    []
    1.84
    push
    1.34
    '][]
    1.17
    ][]
    1.16
     []
    1.13
     push
    1.11
    ()
    1.06
     =
    1.02
     append
    0.99
     PUSH
    0.95
    Activations Density 0.012%

    No Known Activations