© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10646
    Prev
    Next
    INDEX
    Explanations

    specifying details, parameters, or new items

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

    The neuron strongly activates on floating‐point numeric tokens (numbers containing a decimal point).

    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
    ן
    0.76
     sureties
    0.71
    ্ব
    0.71
    WAY
    0.71
    ت
    0.68
    רו
    0.66
    oz
    0.66
    aj
    0.66
    mountain
    0.65
    mber
    0.63
    POSITIVE LOGITS
     системы
    0.91
     болезни
    0.91
     മേഖ
    0.84
     conceito
    0.82
     поскольку
    0.81
     согласно
    0.80
     cálculo
    0.79
     vẫn
    0.78
     sozinha
    0.78
     debería
    0.78
    Activations Density 0.000%

    No Known Activations