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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6089
    Prev
    Next
    INDEX
    Explanations

    certified registered nurse anesthetists

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

    The neuron is highly activated by numeric tokens containing decimal points (e.g., floating‐point reference or citation 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_31_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
     不过
    0.89
    让你
    0.84
    ЕН
    0.80
    让人
    0.80
     quartile
    0.78
    給你
    0.78
    讓你
    0.77
     Ā
    0.76
    ifient
    0.76
    广州
    0.75
    POSITIVE LOGITS
    reements
    0.79
    ようになった
    0.73
     auftreten
    0.72
     важное
    0.71
    ずに
    0.70
     maio
    0.70
    stelling
    0.70
    できるよう
    0.69
     навыки
    0.69
    handlungen
    0.69
    Activations Density 0.000%

    No Known Activations