© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62441
    Prev
    Next
    INDEX
    Explanations

    South Korean pop band BTS

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

    The neuron strongly activates on numeric tokens (e.g. version numbers, error codes, or other digit sequences) in the text.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ătă
    -0.81
    Diam
    -0.79
    mhz
    -0.77
     yyl
    -0.73
    Qa
    -0.72
    FromDB
    -0.71
    膏
    -0.71
    кал
    -0.70
    representations
    -0.70
    ノベーション
    -0.69
    POSITIVE LOGITS
     BTS
    1.65
    BTS
    1.45
     ARMY
    1.09
    bts
    1.07
     Taehyung
    1.05
     Jungkook
    1.03
     bts
    1.02
     Jimin
    0.93
     Seok
    0.93
    نامج
    0.93
    Activations Density 0.010%

    No Known Activations