© 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. 2691
    Prev
    Next
    INDEX
    Explanations

    connective words or phrases

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

    The neuron strongly activates on numeric tokens and numeric expressions (e.g. multi‐digit numbers, times, measurements).

    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
    ,
    0.92
    Whilst
    0.71
    )
    0.66
    í
    0.63
    i
    0.63
     Whilst
    0.62
    IAN
    0.61
    ::
    0.60
    ى
    0.60
    ic
    0.59
    POSITIVE LOGITS
     illetve
    1.09
     czyli
    1.07
     odnosno
    1.04
     respectivamente
    0.96
     porém
    0.95
     albeit
    0.91
     اتارنا
    0.90
     respectively
    0.89
     huh
    0.89
     pero
    0.84
    Activations Density 1.150%

    No Known Activations