© 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. 2675
    Prev
    Next
    INDEX
    Explanations

    processes and phenomena

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

    The neuron strongly activates on specialized scientific and biochemical terminology—particularly molecular, cellular, and chemical process and protein names.

    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
     concentração
    0.64
     nera
    0.63
     avere
    0.63
    ₫
    0.61
     خالی
    0.60
     distribuzione
    0.59
     казиносу
    0.59
    Heute
    0.59
     atheist
    0.58
    얇
    0.58
    POSITIVE LOGITS
     processes
    0.92
     mechanisms
    0.84
     efficiency
    0.83
    过程中
    0.83
     Processes
    0.83
     rates
    0.82
    过程
    0.81
     phenomena
    0.80
     kinetics
    0.80
    processes
    0.79
    Activations Density 0.214%

    No Known Activations