© 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. 5005
    Prev
    Next
    INDEX
    Explanations

    vision, hugging

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

    The main thing this neuron does is detect the word “food.”

    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
     ombil
    0.93
     wojewód
    0.82
     UIAlert
    0.82
    閲
    0.80
     имат
    0.77
     تحتوي
    0.77
    寫
    0.76
    詁
    0.76
     imaju
    0.75
     svjet
    0.75
    POSITIVE LOGITS
     generational
    0.65
     pillar
    0.64
    intern
    0.63
    </h2>
    0.63
     wealth
    0.62
     continuance
    0.62
     links
    0.61
     continued
    0.61
    </blockquote>
    0.60
    Union
    0.60
    Activations Density 0.000%

    No Known Activations