© 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. 11224
    Prev
    Next
    INDEX
    Explanations

    strategy headings

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

    The neuron activates on numeric tokens—especially multi-digit figures such as dates, monetary amounts, statistics, and other raw 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
     quaint
    0.64
    owntown
    0.62
     actifs
    0.61
    告知
    0.60
     papeles
    0.60
     polisi
    0.60
    问
    0.60
     vecchio
    0.59
    告诉
    0.59
     defunct
    0.58
    POSITIVE LOGITS
     astăzi
    0.82
     오늘
    0.74
    Commenting
    0.71
     idag
    0.71
     اليوم
    0.70
     highlights
    0.70
     Président
    0.70
    ™,
    0.69
     Highlights
    0.68
    ™.
    0.68
    Activations Density 0.261%

    No Known Activations