© 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. 117106
    Prev
    Next
    INDEX
    Explanations

    bind and bound

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

    The neuron specifically fires on occurrences of C++ functional-binding constructs (e.g. std::bind, the <functional> header, std::placeholders, etc.).

    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
     bush
    -0.75
    bush
    -0.73
    ágina
    -0.71
     monitor
    -0.71
    CAREER
    -0.69
     BUSH
    -0.69
    lev
    -0.68
    〛
    -0.67
     communiquez
    -0.67
     Bush
    -0.67
    POSITIVE LOGITS
     binding
    3.80
     bind
    3.50
     bound
    3.48
     Binding
    3.48
    bind
    3.36
    binding
    3.17
    Binding
    3.16
     bindings
    3.06
    Bind
    3.06
     Bind
    2.97
    Activations Density 0.065%

    No Known Activations