© 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. 15166
    Prev
    Next
    INDEX
    Explanations

    **wider reach or audience**

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

    The neuron activates on numeric tokens with decimal points (i.e. floating-point numbers) 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
    เดียว
    0.94
    deki
    0.93
    detalle
    0.89
     manteniendo
    0.88
    ാണ്
    0.86
     obwohl
    0.86
    íti
    0.83
    ະ
    0.82
     fehlt
    0.82
     adanya
    0.80
    POSITIVE LOGITS
     美国
    0.76
    рани
    0.71
    чане
    0.68
     everyone
    0.66
     করিলেন
    0.65
     Сою
    0.64
     列
    0.64
     attentively
    0.64
    ives
    0.64
    бри
    0.64
    Activations Density 0.000%

    No Known Activations