© 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. 7640
    Prev
    Next
    INDEX
    Explanations

    project, span, parameter, connected devices

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

    The neuron strongly activates on numeric expressions—digits, decimals, and related numeric tokens (e.g. measurements or monetary values).

    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
     Apoll
    0.83
    ↵
    0.79
     Gender
    0.76
     apron
    0.76
     Jealous
    0.75
    לות
    0.74
     dallo
    0.72
     Emory
    0.72
     পাঁ
    0.71
    archy
    0.71
    POSITIVE LOGITS
    arli
    0.84
    凵
    0.79
    challenged
    0.74
    끙
    0.74
    erai
    0.73
    itimes
    0.72
    ar
    0.72
    ა
    0.72
    OI
    0.71
    ጥ
    0.71
    Activations Density 0.000%

    No Known Activations