© 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. 7815
    Prev
    Next
    INDEX
    Explanations

    Perform NER

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

    The neuron is keyed to spotting numeric expressions—especially measurements, counts, and decimal 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_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
    คือ
    0.91
    เป็น
    0.89
    เพราะ
    0.84
    :
    0.80
     eben
    0.75
     sacré
    0.75
     née
    0.72
     là
    0.70
    ເປັນ
    0.70
     titans
    0.70
    POSITIVE LOGITS
    I
    1.05
    asibility
    0.97
    swering
    0.89
     почвы
    0.88
    laublich
    0.84
    sembled
    0.83
    riminating
    0.83
    ہنی
    0.82
    V
    0.82
    iguous
    0.81
    Activations Density 15.394%

    No Known Activations