© 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. 6132
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    The neuron fires on numeric date, time, and year tokens (e.g. “February,” “4 May,” “2013,” “1982,” “8 am–1 pm,” etc.).

    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
     حقوق
    0.62
     संस्कारों
    0.54
    嗆
    0.54
    மாவட்ட
    0.52
     ఉంటుంది
    0.52
    使用者
    0.52
     sensibles
    0.50
     લોકોને
    0.50
     escuelas
    0.49
     ఉంటాయి
    0.48
    POSITIVE LOGITS
     iaitu
    0.79
     即
    0.78
     onwards
    0.76
    即
    0.72
    自体
    0.70
     Jharkhand
    0.68
     upto
    0.67
     itself
    0.63
     Padukone
    0.63
     Shukla
    0.63
    Activations Density 0.125%

    No Known Activations