© 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. 116552
    Prev
    Next
    INDEX
    Explanations

    Magento code methods and phrases

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

    The neuron strongly activates on PHP object‐method chaining (the “->” operator and its method calls).

    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
    NEXT
    -0.84
     Joo
    -0.72
     Molto
    -0.71
     всички
    -0.71
    æng
    -0.71
     Oye
    -0.71
     menschliche
    -0.71
    Jig
    -0.69
     verità
    -0.69
     tiffany
    -0.69
    POSITIVE LOGITS
    hasData
    0.88
    ZB
    0.81
    ências
    0.80
     Daten
    0.79
     granul
    0.79
     scar
    0.77
    setData
    0.76
     volleyball
    0.75
    LOD
    0.75
     Retrieve
    0.73
    Activations Density 0.018%

    No Known Activations