© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 4991
    Prev
    Next
    INDEX
    Explanations

    The neuron detects reporting‐style verbs that introduce attributed speech or statements (e.g. “reported,” “told,” “said”).

    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
     jellyfish
    0.58
     JHEP
    0.58
     GitLab
    0.57
     சுண்ணா
    0.55
     लेणी
    0.54
    pH
    0.54
    pV
    0.54
    Telex
    0.53
    薅
    0.53
    ⛵
    0.52
    POSITIVE LOGITS
     firearm
    2.53
     handgun
    2.45
     gun
    2.44
     firearms
    2.44
     guns
    2.36
    銃
    2.23
     pistol
    2.19
     gunman
    2.17
    枪
    2.16
     pistols
    2.09
    Activations Density 0.322%

    No Known Activations