© 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. 108888
    Prev
    Next
    INDEX
    Explanations

    angular.module

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

    The neuron fires strongly on occurrences of “angular” (or “Angular”) and its dotted API calls (e.g. “angular.module”), so it’s detecting references to the AngularJS framework.

    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
     Rous
    -0.82
     kolek
    -0.76
     intress
    -0.73
     Belakang
    -0.71
    bonnet
    -0.71
    ЧЕ
    -0.69
    Deuter
    -0.69
    TECHNOLOGY
    -0.68
    bleiben
    -0.68
     Израи
    -0.68
    POSITIVE LOGITS
     module
    1.09
    module
    1.00
    Module
    0.88
    JSONObject
    0.80
     modulus
    0.76
     gering
    0.75
    MODULE
    0.74
     towards
    0.73
    modules
    0.73
    cognised
    0.73
    Activations Density 0.026%

    No Known Activations