© 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. 3709
    Prev
    Next
    INDEX
    Explanations

    arising, produced, or occurring

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

    The neuron is primarily firing on the subordinating conjunction “that” when it introduces a relative or complement clause.

    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
     whom
    0.89
    ที่ไม่
    0.88
    相同的
    0.82
    ам
    0.82
     whereabouts
    0.80
    ที่จะ
    0.79
    це
    0.79
    я
    0.79
    ер
    0.77
     appreciation
    0.76
    POSITIVE LOGITS
     perv
    0.81
     ensues
    0.80
     Congresso
    0.79
     Ünivers
    0.78
     Humans
    0.75
     Crav
    0.75
     către
    0.74
     Anlagen
    0.74
     Chávez
    0.73
     الأوروب
    0.73
    Activations Density 0.344%

    No Known Activations