© 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. 2860
    Prev
    Next
    INDEX
    Explanations

    The neuron is strongly activated by numeric expressions (numbers, dates, or quantities).

    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
     ৩
    0.80
     ৩০০
    0.79
     ৫০০
    0.79
     ৪০০
    0.72
    3
    0.71
    ৩
    0.66
     ३
    0.64
    ３
    0.62
     ৪
    0.61
     ४
    0.59
    POSITIVE LOGITS
     fourteen
    2.09
     sixteen
    2.09
     seventeen
    2.06
     fourteenth
    1.96
     fifteenth
    1.95
     Sixteen
    1.93
     fifteen
    1.92
     thirteen
    1.92
     sixteenth
    1.91
     Fifteen
    1.91
    Activations Density 0.743%

    No Known Activations