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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6828
    Prev
    Next
    INDEX
    Explanations

    it is

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

    The neuron fires on third‐person singular neuter pronouns (e.g. “it,” “its”) in running text.

    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
     lindos
    1.08
    ﻱ
    0.88
    िटी
    0.86
     وعلى
    0.86
     fais
    0.86
     kya
    0.85
     💕
    0.84
    ки
    0.84
    িমে
    0.84
    تها
    0.83
    POSITIVE LOGITS
    ņ
    0.85
    可能です
    0.79
     hypothesize
    0.73
     Partially
    0.71
    vom
    0.70
    য়াছে
    0.68
    տ
    0.67
    सुद्धा
    0.66
    vät
    0.66
     사용하는
    0.66
    Activations Density 0.401%

    No Known Activations