© 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. 13391
    Prev
    Next
    INDEX
    Explanations

    win a Nobel Prize

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

    The neuron selectively activates on floating-point numeric tokens (decimal 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
    texto
    0.93
    archivo
    0.93
    arquivo
    0.86
    بة
    0.84
    walls
    0.83
    չ
    0.83
    mär
    0.82
    ة
    0.80
    texts
    0.79
    ското
    0.78
    POSITIVE LOGITS
    たる
    0.74
     Đo
    0.74
     Sequencing
    0.74
     Nomenclature
    0.73
     tRNA
    0.71
     valuation
    0.70
     lineage
    0.70
     DSG
    0.70
     pedigree
    0.70
     Nested
    0.70
    Activations Density 0.000%

    No Known Activations