© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8390
    Prev
    Next
    INDEX
    Explanations

    agents and action

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

    The neuron is attuned to numerical or quantitative contexts, i.e. words appearing in passages that convey stats, figures, stages, measurements, or other number‐related information.

    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
    чными
    0.88
     honti
    0.86
    帳に追加
    0.86
    aciones
    0.85
    かを
    0.85
    이랑
    0.85
    бы
    0.84
    👭
    0.83
    に行って
    0.82
    től
    0.80
    POSITIVE LOGITS
     
    0.83
    야
    0.82
     large
    0.81
     Ust
    0.75
     designed
    0.75
     設計
    0.75
    jay
    0.74
    <h2>
    0.72
    yer
    0.72
    大型
    0.71
    Activations Density 0.000%

    No Known Activations