© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5189
    Prev
    Next
    INDEX
    Explanations

    This neuron fires strongly on the very first meaningful (non‐stop) word at the start of a new paragraph or section.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     contrô
    0.74
     colonel
    0.73
     comical
    0.73
    प्टेंबर
    0.71
    ඔ
    0.69
     thành
    0.68
     Lebih
    0.68
    丰富的
    0.68
     condesc
    0.67
     chemins
    0.67
    POSITIVE LOGITS
    на
    0.79
    reminder
    0.79
    <0x80>
    0.74
    ות
    0.72
    someone
    0.71
    ﻛ
    0.71
    ención
    0.70
    olicy
    0.70
    enc
    0.70
    ที่จะ
    0.69
    Activations Density 0.000%

    No Known Activations