© 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. 3909
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is detect very high‐frequency/common words across contexts.

    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
    SL
    0.72
     Cons
    0.70
     em
    0.70
    全面
    0.68
    Tl
    0.68
     kẻ
    0.68
    ()");
    0.66
    ();}
    0.66
     thé
    0.63
    Sco
    0.63
    POSITIVE LOGITS
     представить
    0.94
     situaciones
    0.78
    ிருஷ்
    0.76
     ámbitos
    0.75
    laştır
    0.75
    falen
    0.72
    тивы
    0.72
    ்ட்
    0.71
    ्तिक
    0.71
     carbides
    0.71
    Activations Density 0.001%

    No Known Activations