© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71821
    Prev
    Next
    INDEX
    Explanations

    new object creation

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

    The neuron detects occurrences of the C# “new” keyword (object instantiations).

    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
     como
    -1.07
    ыргыз
    -1.02
    anneer
    -1.02
     怎样
    -0.99
     функции
    -0.98
     mediante
    -0.98
    jego
    -0.98
    ulation
    -0.98
    이션
    -0.96
     Körpers
    -0.96
    POSITIVE LOGITS
     now
    1.00
     käytet
    0.99
     <",
    0.99
    ➨
    0.96
    /
    0.95
     about
    0.93
     egens
    0.92
     montagnes
    0.88
     pantolon
    0.87
     IEnumerable
    0.85
    Activations Density 0.005%

    No Known Activations