© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5165
    Prev
    Next
    INDEX
    Explanations

    establish or setup

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

    The main thing this neuron does is detect the word “establish” (and its close morphological variants like establishes, establishing).

    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_31_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
     redesign
    0.77
     Auswirkungen
    0.76
     разработки
    0.68
     appended
    0.66
     advancements
    0.65
     redesigned
    0.65
     עד
    0.64
     निर्ण
    0.63
    披
    0.63
     innovations
    0.63
    POSITIVE LOGITS
    Establish
    1.04
     estabelecer
    0.94
    establish
    0.93
     establish
    0.92
    Establishing
    0.92
     établir
    0.87
     Establish
    0.86
     étab
    0.85
    établir
    0.84
     établi
    0.84
    Activations Density 0.256%

    No Known Activations