© 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. 22-GEMMASCOPE-RES-131K
    7. 67916
    Prev
    Next
    INDEX
    Explanations

    runners facility, clinics, associated

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

    The neuron activates on jQuery event-binding constructs (e.g. “.on(…)” and “$(…).ready(function…){…}”).

    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
     samoz
    -0.88
    ulatum
    -0.82
     individual
    -0.81
     המצ
    -0.81
     obſ
    -0.80
    单击
    -0.79
    forall
    -0.78
     prega
    -0.76
     سلی
    -0.75
    elman
    -0.74
    POSITIVE LOGITS
     indirectly
    1.15
    indirect
    0.96
    Associated
    0.96
     related
    0.91
     associated
    0.89
     Associated
    0.89
    associated
    0.86
     Marxism
    0.84
     Indirect
    0.84
    一样的
    0.83
    Activations Density 0.127%

    No Known Activations