© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6410
    Prev
    Next
    INDEX
    Explanations

    late 2023/early 2024

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

    The neuron strongly activates on numeric tokens—especially multi‐digit numbers, percentages, and decimal values.

    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_31_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
     például
    1.20
     esimerkiksi
    1.14
     například
    1.08
     Escherichia
    1.04
     soltanto
    1.02
     cerebrospinal
    1.02
     ‌
    1.00
    さまざまな
    0.96
    <0xE2>
    0.93
     beispielsweise
    0.93
    POSITIVE LOGITS
     đc
    2.14
     yg
    1.95
     ppl
    1.90
     yrs
    1.89
     Govt
    1.80
     govt
    1.77
    ってる
    1.73
     dgn
    1.61
     aprox
    1.61
     Dept
    1.58
    Activations Density 0.995%

    No Known Activations