© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7422
    Prev
    Next
    INDEX
    Explanations

    code completion

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

    The neuron strongly responds to occurrences of the name “Eugenio” (and its variants like Eugene/Eugen).

    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
     {/*
    0.61
     forgive
    0.61
    ām
    0.61
     وغير
    0.61
    ūs
    0.60
    ývá
    0.59
     feedwater
    0.59
    īd
    0.59
    リーズ
    0.58
    牀
    0.58
    POSITIVE LOGITS
    קים
    0.54
    CCE
    0.52
     NOI
    0.50
    伴
    0.50
    endants
    0.49
    atiques
    0.49
    जवळ
    0.49
    нду
    0.49
    ^
    0.48
    Bounce
    0.47
    Activations Density 0.003%

    No Known Activations