© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14469
    Prev
    Next
    INDEX
    Explanations

    word parts, letter combinations

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

    The neuron activates strongly on decimal numbers (numeric tokens containing a period).

    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
    en
    0.93
     extraordinaire
    0.83
     Zahlung
    0.80
     ទ
    0.80
     appellee
    0.79
     ถ
    0.79
    ور
    0.78
     siehe
    0.77
     mycket
    0.77
    涷
    0.77
    POSITIVE LOGITS
    criar
    0.75
    created
    0.71
     Durham
    0.70
    ことなく
    0.69
    rumah
    0.68
    md
    0.68
    বাংলার
    0.68
    recently
    0.66
    then
    0.65
    翳
    0.65
    Activations Density 0.000%

    No Known Activations