© 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. 24-GEMMASCOPE-2-RES-16K
    7. 5257
    Prev
    Next
    INDEX
    Explanations

    submitting tasks or requests

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

    The neuron picks out numeric metadata tokens—dates, times, and related numbers (often around “submitted,” “published,” or “by”) in document headers.

    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_24_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
     написать
    0.89
     realice
    0.81
    izes
    0.78
     اكتب
    0.78
    เขียน
    0.77
    썻
    0.75
     δεν
    0.74
    aremos
    0.73
     написал
    0.73
     написа
    0.72
    POSITIVE LOGITS
     revisiting
    0.69
     penggem
    0.69
    共和国
    0.68
     partisans
    0.67
    صرية
    0.67
     pravo
    0.66
     stupe
    0.66
     Reap
    0.66
     Maret
    0.66
    ْد
    0.66
    Activations Density 0.040%

    No Known Activations