© 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. 14322
    Prev
    Next
    INDEX
    Explanations

    US, next week, account names, human average

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

    The neuron activates on tokens representing floating‐point numbers (numerical values 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
    라
    0.84
    دة
    0.79
    دت
    0.77
     सीमाओं
    0.75
    syntax
    0.74
    که
    0.73
    dynamical
    0.73
    yssey
    0.72
    >..\
    0.71
    哮
    0.70
    POSITIVE LOGITS
     catchment
    0.82
     trasform
    0.75
     transform
    0.75
     cargas
    0.74
    ੰਜ
    0.74
     breeding
    0.72
     cemetery
    0.72
     industri
    0.72
     nursery
    0.72
     gastric
    0.72
    Activations Density 0.000%

    No Known Activations