© 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. 2840
    Prev
    Next
    INDEX
    Explanations

    pronunciation explanations

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

    The neuron chiefly activates on numeric tokens (years, quantities, percentages, and other 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_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
    <strong>
    1.09
    ・・・
    1.02
    。。。
    0.97
    。。。。
    0.96
    <b>
    0.95
    ～～
    0.86
    ・・・・
    0.86
    ================
    0.82
    До
    0.82
    кает
    0.81
    POSITIVE LOGITS
    ­
    1.95
     impor
    1.90
     elec
    1.88
     indi
    1.84
     socalled
    1.83
     tions
    1.81
     ­
    1.80
     wellknown
    1.80
     condi
    1.78
     construc
    1.74
    Activations Density 0.256%

    No Known Activations