© 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. 10867
    Prev
    Next
    INDEX
    Explanations

    code comments or specific syntax

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

    The neuron fires strongly on sequences of digits that form personal contact details—particularly street addresses and phone numbers.

    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
     gyerek
    0.68
    杀了
    0.58
    怼
    0.58
     criança
    0.57
    agricult
    0.57
     ederim
    0.57
    小学生
    0.56
     scompar
    0.55
    辈
    0.55
    cliente
    0.55
    POSITIVE LOGITS
     Various
    0.88
     Terms
    0.86
     Figures
    0.80
     Records
    0.77
     Unfortunately
    0.73
     Fortunately
    0.73
     Viewing
    0.72
     Establishing
    0.71
     Yet
    0.71
     Remember
    0.71
    Activations Density 0.001%

    No Known Activations