© 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. 8955
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric 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
     aaye
    0.94
     enkele
    0.91
    kom
    0.88
    (!$
    0.84
    ku
    0.81
     komp
    0.80
    Ошибка
    0.80
    haal
    0.80
    eku
    0.80
    ございます
    0.79
    POSITIVE LOGITS
    <0xBC>
    0.88
     从
    0.75
    に
    0.70
    从
    0.67
    에
    0.66
     河
    0.66
    नगर
    0.65
    хия
    0.64
    dě
    0.64
     উৎসাহ
    0.64
    Activations Density 0.000%

    No Known Activations