© 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. 10-GEMMASCOPE-RES-131K
    7. 58171
    Prev
    Next
    INDEX
    Explanations

    BT

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

    The neuron is detecting the two‐letter uppercase token “BT” (i.e. that specific acronym).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    疴
    -3.08
    .“
    -2.86
     MUCH
    -2.61
    是大
    -2.50
    是個
    -2.45
    鈇
    -2.42
    くない
    -2.36
     That
    -2.33
     “
    -2.31
    だけです
    -2.31
    POSITIVE LOGITS
    矬
    2.86
    餿
    2.69
    ⎚
    2.64
     ouverture
    2.63
    dshaw
    2.56
     считается
    2.55
    ни
    2.55
     "
    2.48
     вызывает
    2.48
     outspoken
    2.45
    Activations Density 0.006%

    No Known Activations