© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30923
    Prev
    Next
    INDEX
    Explanations

    instantiate or create objects

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

    The neuron is highly activated by code‐style identifiers (especially capitalized class or variable names) and storyboard/ViewController instantiation 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
    Comput
    -0.72
    pués
    -0.70
     Izzy
    -0.69
     mạch
    -0.67
    espół
    -0.65
    isNullOrEmpty
    -0.64
     Comput
    -0.63
     perpetuity
    -0.63
     Glee
    -0.63
    idered
    -0.62
    POSITIVE LOGITS
     instantiate
    4.16
     Instantiate
    3.77
     Inst
    3.73
    instantiate
    3.70
     instantiation
    3.66
     instanti
    3.64
    Instantiate
    3.59
     instantiated
    3.47
     inst
    3.42
    Inst
    3.36
    Activations Density 0.305%

    No Known Activations