© 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. 22-GEMMASCOPE-RES-131K
    7. 39007
    Prev
    Next
    INDEX
    Explanations

    angular module definition

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

    The neuron fires on the “angular.module” pattern (i.e. AngularJS module definitions).

    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
    ByPrimaryKey
    -1.07
    jarati
    -1.05
     appartamento
    -1.02
    多く
    -0.99
     betont
    -0.98
    prnewswire
    -0.98
    atalos
    -0.96
     zuhause
    -0.96
     такие
    -0.95
    ………
    -0.94
    POSITIVE LOGITS
    娱乐圈
    1.01
     fosfor
    1.00
     reguli
    1.00
    بله
    0.97
     of
    0.96
     foton
    0.95
    Marta
    0.94
     solida
    0.94
    私の
    0.93
    keyColumn
    0.92
    Activations Density 0.006%

    No Known Activations