© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9940
    Prev
    Next
    INDEX
    Explanations

    The neuron fires most strongly on main event-denoting content words—especially past-tense action verbs that mark key narrative moments.

    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
    ↵↵
    0.65
     (
    0.65
     другое
    0.59
     ANOTHER
    0.59
     anderer
    0.57
    .
    0.56
    其他
    0.56
     elsewhere
    0.56
     ailleurs
    0.56
     otro
    0.55
    POSITIVE LOGITS
     mainly
    0.82
    mainly
    0.78
     głównie
    0.78
     основном
    0.77
     hauptsächlich
    0.77
    主要是
    0.75
     nhưng
    0.72
    不仅
    0.72
    했고
    0.72
     principalement
    0.70
    Activations Density 0.383%

    No Known Activations