© 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. 4016
    Prev
    Next
    INDEX
    Explanations

    of money

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

    The neuron strongly activates on numeric tokens—especially floating‐point 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_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
    t
    0.94
    ()
    0.87
    x
    0.86
    ture
    0.82
    in
    0.73
    ).
    0.71
    )
    0.70
     Report
    0.69
    xls
    0.69
    filled
    0.68
    POSITIVE LOGITS
     niekoľ
    0.95
    就已经
    0.94
    zelf
    0.91
     néhány
    0.88
    <unused1879>
    0.84
    也许
    0.83
     awọn
    0.83
    とその
    0.83
    就需要
    0.82
     lancéolées
    0.82
    Activations Density 1.164%

    No Known Activations