© 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. 11650
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on interjections and discourse markers (e.g. “Oh,” “Okay,” “Well”) that signal shifts in tone or topic.

    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
    ,
    1.30
    ↵
    0.84
    iation
    0.77
     (
    0.76
     distribution
    0.74
    y
    0.74
     collection
    0.73
    .
    0.72
     ,
    0.71
     re
    0.70
    POSITIVE LOGITS
    𝗸
    1.02
    Также
    1.02
     लेकिन
    0.98
    también
    0.98
    あります
    0.96
    También
    0.96
    ﺮ
    0.96
    可惜
    0.95
     მაგრამ
    0.93
    𝗵
    0.93
    Activations Density 0.005%

    No Known Activations