© 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. 15951
    Prev
    Next
    INDEX
    Explanations

    time periods and units

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

    The neuron strongly activates on numeric tokens that include decimal points (i.e. 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
     tannins
    0.72
     mici
    0.71
     fined
    0.69
     sveta
    0.66
     П
    0.66
     lic
    0.63
     drugs
    0.61
     Tinker
    0.61
     Они
    0.61
     అ
    0.60
    POSITIVE LOGITS
    ar
    1.10
    idam
    1.00
    स्ताना
    0.96
    ี
    0.95
    irthday
    0.92
     ошибок
    0.92
    odz
    0.91
    iz
    0.90
     eleições
    0.90
    appearing
    0.88
    Activations Density 0.000%

    No Known Activations