© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14658
    Prev
    Next
    INDEX
    Explanations

    Eisenhower Matrix

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

    The neuron is selectively activating on numeric tokens formatted as floating-point (decimal) numbers.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    铁路
    0.77
    プリ
    0.75
     наси
    0.73
    Medico
    0.71
    的总
    0.71
    届
    0.69
    DanhMuc
    0.68
     Cush
    0.68
    Cert
    0.68
    DropDownItem
    0.66
    POSITIVE LOGITS
    8
    0.87
     trusty
    0.83
    س
    0.79
     best
    0.76
     leaderboard
    0.76
     spies
    0.75
    ión
    0.74
     beste
    0.74
    9
    0.74
    inde
    0.73
    Activations Density 0.001%

    No Known Activations