© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10809
    Prev
    Next
    INDEX
    Explanations

    angular

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

    The neuron strongly activates on mentions of the Angular framework (including “Angular,” version numbers, and its technical terms and features).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Edo
    0.66
     Kupp
    0.59
     slit
    0.57
     슬
    0.57
     Oss
    0.56
     చెర్రీ
    0.56
     osu
    0.55
    굼
    0.55
     Schr
    0.54
     sakura
    0.54
    POSITIVE LOGITS
     AngularJS
    1.30
     angular
    1.13
    angular
    1.05
    Angular
    0.97
     Angular
    0.96
     ['$
    0.86
    ngModel
    0.76
     controllers
    0.72
     Controllers
    0.71
     orderBy
    0.70
    Activations Density 0.006%

    No Known Activations