© 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. 34-GEMMASCOPE-RES-131K
    7. 78016
    Prev
    Next
    INDEX
    Explanations

    navigation and programming code

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

    The neuron fires on code patterns accessing the React Native navigation prop chain (e.g. this.props.navigation.state.params).

    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
     riun
    -0.79
     Jede
    -0.78
    ieren
    -0.77
     Reine
    -0.76
     apollo
    -0.75
     Guid
    -0.75
     Ier
    -0.74
    ereco
    -0.73
    られています
    -0.72
     bair
    -0.72
    POSITIVE LOGITS
    getParam
    0.88
    setOptions
    0.83
     oficinas
    0.80
    Param
    0.80
    navigate
    0.80
    geolocation
    0.79
     państw
    0.77
    zhan
    0.77
     turysty
    0.76
     ligero
    0.75
    Activations Density 0.003%

    No Known Activations