© 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. 2972
    Prev
    Next
    INDEX
    Explanations

    The neuron fires almost exclusively on the very first substantive word after a new “<start>” or section boundary, marking the beginning of each document segment.

    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
    ucker
    0.70
    า
    0.70
    sag
    0.67
    اگ
    0.67
    abod
    0.66
    나
    0.66
    rivation
    0.65
    aré
    0.64
    dru
    0.64
    간
    0.64
    POSITIVE LOGITS
     undermines
    0.97
     Když
    0.89
     uygulan
    0.88
     относится
    0.86
     kuri
    0.84
     provinsi
    0.84
     nogen
    0.84
     Bupati
    0.82
     MgII
    0.82
     sensed
    0.82
    Activations Density 0.000%

    No Known Activations