© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7615
    Prev
    Next
    INDEX
    Explanations

    words starting with Pr

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

    This neuron detects tokens beginning with the letter sequence “Pr” (especially “Pra…”) such as proper names or terms like Pragya or Pragma.

    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
     теркәлү
    0.71
    WidgetItem
    0.65
     букмекерлер
    0.61
    డు
    0.61
    মান্ড
    0.61
     cốt
    0.61
    分鐘
    0.59
    <unused78>
    0.58
     депозиттик
    0.58
    గం
    0.58
    POSITIVE LOGITS
     Pr
    1.23
    Pr
    1.23
     Pratt
    0.97
     PR
    0.92
     Prat
    0.86
     Priscilla
    0.83
     pr
    0.81
    pr
    0.80
     Prins
    0.79
     Пра
    0.79
    Activations Density 0.202%

    No Known Activations