© 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. 13828
    Prev
    Next
    INDEX
    Explanations

    ASCII art and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on any token beginning with the letters “As” (in upper‐ or title‐case).

    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
    ूप
    0.59
     newest
    0.59
     Sakurai
    0.59
     sparked
    0.57
     शहनाज
    0.57
     решения
    0.57
    िद
    0.57
     sprem
    0.57
    撅
    0.57
    稹
    0.57
    POSITIVE LOGITS
     אס
    0.75
     AS
    0.71
     Asp
    0.71
    ASP
    0.71
    Assassin
    0.69
    ASCII
    0.68
     Asc
    0.68
     ασ
    0.67
     অ্যাস
    0.66
     ас
    0.65
    Activations Density 0.256%

    No Known Activations