© 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. 98821
    Prev
    Next
    INDEX
    Explanations

    liability for, supra shoes, telegrams

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

    This neuron detects tokens that are capitalized proper nouns or acronyms (i.e. named entities).

    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
     a
    -1.57
    ’
    -1.53
    去看
    -1.41
    懂得
    -1.41
     ”
    -1.40
    店で
    -1.38
     drinking
    -1.37
     Überras
    -1.33
     aberta
    -1.33
    してた
    -1.33
    POSITIVE LOGITS
    they
    1.66
    because
    1.46
    too
    1.45
     they
    1.43
    before
    1.42
    begin
    1.42
    为什么
    1.40
     miguel
    1.39
    ✔
    1.38
    within
    1.34
    Activations Density 0.069%

    No Known Activations