© 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. 3353
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on tokens containing apostrophes—i.e. possessive ’s or contractions/quoted fragments.

    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
    و
    0.69
     Vedas
    0.66
     prothorax
    0.64
     teilen
    0.62
     condivid
    0.62
    u
    0.62
     tienes
    0.61
     ungefähr
    0.61
     NCBI
    0.60
    کلی
    0.60
    POSITIVE LOGITS
    ’
    0.66
    檚
    0.64
    .
    0.62
    ゙
    0.56
    𝗲
    0.56
    edly
    0.54
    ized
    0.54
     ‪
    0.54
    ــــ
    0.53
    ious
    0.52
    Activations Density 0.221%

    No Known Activations