© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39193
    Prev
    Next
    INDEX
    Explanations

    `function` or `undefined` followed by `(` or `console`

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

    This neuron detects numeric literals in code, i.e. tokens consisting of digits (version numbers, constants, 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_22/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
    xe
    -0.97
    tocks
    -0.96
    rule
    -0.94
     См
    -0.94
    hadas
    -0.94
     diputados
    -0.92
     стола
    -0.92
    ño
    -0.92
    greens
    -0.91
    alucía
    -0.89
    POSITIVE LOGITS
    ఒ
    1.16
     लेकिन
    0.95
     між
    0.93
    もあって
    0.91
     ولكن
    0.90
     แต่
    0.89
    ஒ
    0.86
     nhưng
    0.85
     野球
    0.84
    ซื้อ
    0.83
    Activations Density 0.006%

    No Known Activations