© 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. 2720
    Prev
    Next
    INDEX
    Explanations

    potential followed by issue or risk

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

    This neuron specializes in picking up the C/C++ attribute token sequence “maybe_unused” (i.e. the [[maybe_unused]] annotation).

    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
     with
    -0.87
     miei
    -0.86
    俱乐
    -0.81
     Jerman
    -0.77
     बिना
    -0.77
     Políticas
    -0.76
    고
    -0.75
    ゜
    -0.75
     часу
    -0.75
     without
    -0.73
    POSITIVE LOGITS
     itr
    1.06
     زیرا
    1.05
    짭
    0.94
    硼
    0.91
     obsah
    0.91
     ww
    0.89
     rác
    0.88
    窈
    0.88
     herum
    0.87
    ਲ਼
    0.87
    Activations Density 0.034%

    No Known Activations