© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12847
    Prev
    Next
    INDEX
    Explanations

    template, tempo, temper

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

    This neuron activates on tokens beginning with the substring “temp” (e.g., temp-, templ-, tempo-).

    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
    ี่ยม
    0.61
    opolys
    0.61
     لطف
    0.58
     Oliv
    0.57
     bato
    0.57
    烃
    0.57
     Nowak
    0.57
    చ్చ
    0.56
     تربیت
    0.55
    缁
    0.55
    POSITIVE LOGITS
    庙
    0.81
    tem
    0.74
     tantrums
    0.68
     ton
    0.66
     tem
    0.65
     muita
    0.64
    Temper
    0.64
    廟
    0.64
    amental
    0.61
    templat
    0.61
    Activations Density 0.102%

    No Known Activations