© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 87040
    Prev
    Next
    INDEX
    Explanations

    angular.js $http calls

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

    The neuron fires on AngularJS dependency‐injection tokens (e.g. service/provider names like $http, $state, $location, $route, $modal, provide).

    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
     anderen
    -1.56
     and
    -1.50
    每個
    -1.43
    多谢
    -1.41
     klasa
    -1.39
    kasi
    -1.35
    thx
    -1.34
     other
    -1.34
     but
    -1.33
     jungen
    -1.32
    POSITIVE LOGITS
    derung
    1.53
    
    1.51
     you
    1.49
    缓慢
    1.45
     elog
    1.45
    LINE
    1.44
    ten
    1.41
    vaded
    1.41
    cję
    1.39
    uyasha
    1.39
    Activations Density 0.001%

    No Known Activations