© 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. 10864
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numerical tokens containing decimal points (floating‐point 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
     prenant
    0.97
    据悉
    0.89
    するなど
    0.89
     raczej
    0.86
    ždy
    0.85
    తుందని
    0.85
     związ
    0.83
    ö
    0.82
     mentales
    0.80
     conflit
    0.80
    POSITIVE LOGITS
    U
    0.78
    xq
    0.76
     пользоваться
    0.75
    asd
    0.74
    ي
    0.74
    ASTIC
    0.73
    m
    0.73
    employed
    0.71
    mq
    0.71
    INotification
    0.71
    Activations Density 0.000%

    No Known Activations