© 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. 54066
    Prev
    Next
    INDEX
    Explanations

    allocating new objects

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

    The neuron fires on uses of the C++ “new” operator (i.e. heap memory allocations).

    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
     wciąż
    -0.82
     mentre
    -0.81
    𝐩
    -0.80
     quedó
    -0.80
     advice
    -0.79
    сная
    -0.78
    发了
    -0.78
    ButtonModule
    -0.78
    をします
    -0.78
     tüm
    -0.77
    POSITIVE LOGITS
    ॄ
    0.87
    ὁ
    0.82
     (
    0.80
    🧨
    0.79
    皋
    0.79
     кстати
    0.79
     Ше
    0.79
    Dienst
    0.78
    foly
    0.78
     heet
    0.77
    Activations Density 0.007%

    No Known Activations