© 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. 10060
    Prev
    Next
    INDEX
    Explanations

    equivalent position

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

    The main thing this neuron does is detect numeric expressions (numbers, percentages, measurements, and other digit-based tokens).

    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
     клиент
    0.75
     franchisee
    0.74
     corporates
    0.73
    老板
    0.72
    🏭
    0.70
     eCommerce
    0.70
    老闆
    0.70
     영업
    0.68
     કંપની
    0.68
     corporate
    0.68
    POSITIVE LOGITS
    聘
    0.59
     appointment
    0.59
     Posts
    0.59
     deficit
    0.58
     Teaching
    0.58
    rical
    0.57
     Appointment
    0.57
     hires
    0.57
     Hiring
    0.56
    accumulation
    0.55
    Activations Density 0.126%

    No Known Activations