© 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. 11676
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on the word “diagnosis.”

    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
    Time
    1.01
    くれる
    0.82
    ت
    0.82
    D
    0.80
    T
    0.79
    I
    0.78
    ن
    0.76
    ed
    0.75
    V
    0.71
    ized
    0.71
    POSITIVE LOGITS
    ।''
    0.80
    stvu
    0.77
     diagonalizable
    0.76
     RasterModelGrid
    0.74
    uyoruz
    0.74
     lemmas
    0.74
     وعلى
    0.73
     ইন্দুর
    0.72
     mũ
    0.72
     পিটার
    0.72
    Activations Density 0.000%

    No Known Activations