© 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. 24-GEMMASCOPE-2-RES-16K
    7. 2051
    Prev
    Next
    INDEX
    Explanations

    language switching

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

    The neuron strongly activates on terms describing environmental pollution incidents—especially oil spills—and related cleanup, compensation, and affected‐region remediation language.

    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
     නමුත්
    0.63
    Determination
    0.61
     ؛
    0.60
    ﭥ
    0.59
     които
    0.59
    Hearing
    0.58
    銠
    0.58
     તરીકે
    0.57
    الإ
    0.57
    的情況
    0.57
    POSITIVE LOGITS
     그러
    0.77
     그
    0.70
     bunun
    0.66
     이런
    0.65
     böyle
    0.64
     bugün
    0.63
     제대로
    0.62
     bunu
    0.61
     지난
    0.61
     그것
    0.60
    Activations Density 0.009%

    No Known Activations