© 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. 24-GEMMASCOPE-2-RES-16K
    7. 11568
    Prev
    Next
    INDEX
    Explanations

    numbers and units like kg, percent, ratio

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

    The neuron responds to numeric tokens—especially decimal numbers or other multi‐digit number sequences.

    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
    am
    0.93
    en
    0.89
    e
    0.85
    i
    0.83
    yad
    0.82
     Raghav
    0.81
    el
    0.81
    BURG
    0.79
    ebay
    0.78
    \,.
    0.77
    POSITIVE LOGITS
     ενός
    0.74
    鳧
    0.74
    だと
    0.73
    에서는
    0.73
    جی
    0.72
    小時
    0.71
    じ
    0.71
    할
    0.70
    த்தில்
    0.69
    하는
    0.69
    Activations Density 0.001%

    No Known Activations