© 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. 10-GEMMASCOPE-RES-131K
    7. 15109
    Prev
    Next
    INDEX
    Explanations

    private instance field declarations

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

    This neuron activates on visibility modifiers—especially the keyword “private” on member declarations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    '
    -3.20
     
    -3.09
     they
    -2.94
    {
    -2.67
    "
    -2.64
    </h3>
    -2.63
    </strong>
    -2.55
    ↵↵
    -2.52
    1
    -2.48
    )
    -2.22
    POSITIVE LOGITS
    ჻
    2.92
    ”，
    2.83
    Благодаря
    2.72
    玧
    2.72
    🌻
    2.70
    ☫
    2.69
    遢
    2.67
    Однако
    2.61
     readonly
    2.56
    "];
    2.52
    Activations Density 0.017%

    No Known Activations