© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9303
    Prev
    Next
    INDEX
    Explanations

    daily frequency

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

    The neuron activates on numeric tokens (quantities, statistics, measurements) in the text.

    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
    暨
    0.71
    其中
    0.69
    middels
    0.69
    Pe
    0.69
     partiellement
    0.68
    przy
    0.68
    ూ
    0.68
    が大
    0.68
    Bal
    0.67
    指挥
    0.67
    POSITIVE LOGITS
     each
    1.91
     setiap
    1.81
     каждой
    1.79
     every
    1.77
     mỗi
    1.77
     каждый
    1.74
     каждого
    1.71
     каждую
    1.70
     varje
    1.63
     каждое
    1.62
    Activations Density 0.970%

    No Known Activations