© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5610
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by occurrences of the words “before” or “after” (and related phrases) marking temporal or comparative transitions.

    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_31_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
    ুদ্ধ
    0.66
    是的
    0.62
    অর্থাৎ
    0.60
    োধী
    0.59
    
    0.56
    вица
    0.55
    rät
    0.54
    admins
    0.54
    ческой
    0.53
     cores
    0.53
    POSITIVE LOGITS
    mentioned
    0.67
     Last
    0.66
    コロナ
    0.65
    ヮ
    0.62
     jurídico
    0.61
     reproach
    0.59
    Ferg
    0.59
    ের
    0.59
    czas
    0.59
     vulgar
    0.59
    Activations Density 0.581%

    No Known Activations