© 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. 7104
    Prev
    Next
    INDEX
    Explanations

    component mounting and unmounting

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

    The neuron flags code tokens related to mounting and unmounting (e.g. componentDidMount, componentWillUnmount, enzyme mount, didMoveToParentViewController).

    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
    跟她
    -1.73
     ส์
    -1.66
    either
    -1.64
     diferite
    -1.63
    one
    -1.60
     diversos
    -1.59
     zelfs
    -1.59
     Ciências
    -1.58
     trabalhos
    -1.58
     muitas
    -1.58
    POSITIVE LOGITS
     But
    2.53
    \
    1.95
          
    1.77
     inuti
    1.70
     huge
    1.69
    Surprisingly
    1.62
    There
    1.62
    ers
    1.59
    Putting
    1.56
    You
    1.55
    Activations Density 0.001%

    No Known Activations