© 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-4-31B-IT
    5. Neurons
    7. 2
    9. 6
    Prev
    Next
    INDEX
    Explanations

    text tokenization or segmentation artifacts, particularly instances where the letter "l" appears as an isolated token boundary.

    oai_token-act-pair · claude-4-5-haikuTriggered by @johnny

    l

    np_max-act-logits · claude-4-5-haikuTriggered by @johnny
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    No Known Activations