© 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. 3565
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on low-frequency, content-rich tokens—e.g. technical terms, acronyms, proper nouns, or numbers—i.e. rare or specialized vocabulary.

    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
     விரிவா
    0.63
     빌
    0.56
     revisiting
    0.55
    鬆
    0.55
     grö
    0.55
     ಬೆ
    0.55
     پیپلز
    0.55
     खुला
    0.54
    釋
    0.54
    ಹಾರ
    0.54
    POSITIVE LOGITS
     prohibiting
    2.95
    禁止
    2.88
     prohibition
    2.83
     запре
    2.81
     prohibitions
    2.80
     restriction
    2.78
     restricting
    2.78
     prohib
    2.69
     prohibits
    2.59
     restrictions
    2.56
    Activations Density 1.383%

    No Known Activations