© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 799
    Prev
    Next
    INDEX
    Explanations

    resolve URLs, functions, or variables

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

    The neuron fires on tokens related to “resolve” (and its past-tense form “resolved”), e.g. function or field names and JSON keys containing “resolve.”

    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
    ليب
    -0.82
     pół
    -0.80
     CONCLUSION
    -0.80
     multer
    -0.77
     לכ
    -0.77
     Allu
    -0.74
    饥
    -0.73
    床
    -0.73
    飢
    -0.72
     realize
    -0.70
    POSITIVE LOGITS
    Resolve
    1.18
    resol
    1.15
    resolve
    1.04
     Resolve
    1.03
     resolving
    0.97
     resolutions
    0.90
     Resolution
    0.89
    problem
    0.89
     resolve
    0.89
     Auflösung
    0.88
    Activations Density 0.006%

    No Known Activations