© 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. 34-GEMMASCOPE-RES-131K
    7. 76911
    Prev
    Next
    INDEX
    Explanations

    dependencies and effects

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

    The neuron detects occurrences of the React Hook “useEffect.”

    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
    rinhos
    -0.83
    /#/
    -0.77
    ILLING
    -0.77
    九月
    -0.76
     Traité
    -0.73
    ((((
    -0.73
     aho
    -0.71
    межу
    -0.71
    =((
    -0.71
    痣
    -0.71
    POSITIVE LOGITS
     dependencies
    1.09
    },[
    1.00
    dependencies
    0.99
     deps
    0.99
     dependency
    0.99
    Deps
    0.98
    deps
    0.96
     Dependency
    0.95
     effect
    0.90
     Effect
    0.89
    Activations Density 0.003%

    No Known Activations