© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 316
    Prev
    Next
    INDEX
    Explanations

    function calls and variable assignments

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

    The neuron reliably lights up on AngularJS controller code that assigns to a scope property—particularly lines where something like `$scope.selectedScript = …` appears.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     победы
    -1.19
     covid
    -1.09
    itir
    -1.02
    XPATH
    -1.02
     AMAZING
    -1.01
     geliefert
    -1.01
    pandemic
    -0.99
     DEI
    -0.99
     DIFFERENT
    -0.98
     gesammelt
    -0.98
    POSITIVE LOGITS
    日を
    1.20
     forem
    1.20
    曲は
    1.13
    ختی
    1.07
    注意事項
    1.05
    🖕
    1.04
    話の
    1.02
    ﺅ
    1.02
     GEORGIA
    1.02
     berken
    1.01
    Activations Density 0.010%

    No Known Activations