© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 4482
    Prev
    Next
    INDEX
    Explanations

    The neuron activates for `super` calls in constructors or methods, and for `@override` annotations in class definitions. It seems to relate to object-oriented programming, specifically inheritance and method overriding.Therefore, a good explanation would capture this.Let's check the constraints:-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tional
    1.28
    t
    1.25
    ד
    1.06
    не
    0.96
    و
    0.96
    ب
    0.95
    m
    0.95
    ei
    0.92
    tion
    0.91
    tch
    0.90
    POSITIVE LOGITS
     incluida
    0.97
     учета
    0.96
    μό
    0.94
    ists
    0.93
    izza
    0.93
     Indones
    0.93
     Excellency
    0.93
     предыду
    0.92
     Rij
    0.91
    َع
    0.91
    Activations Density 0.044%

    No Known Activations