© 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. 45697
    Prev
    Next
    INDEX
    Explanations

    viewDidLoad code and Bayer process

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

    The neuron fires on mentions of “Bay…”–in particular proper names like Bayer (and similarly spelled Baylor).

    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
    辄
    -3.22
     preferido
    -2.53
     espoir
    -2.48
    婓
    -2.38
     apprehensive
    -2.38
    ции
    -2.38
     sucedido
    -2.36
    媖
    -2.36
    砦
    -2.34
    nitř
    -2.31
    POSITIVE LOGITS
     and
    3.36
    .
    3.05
    2
    2.48
    )
    2.44
    <td>
    2.41
     vollständige
    2.36
    我們
    2.36
     Gedanke
    2.28
     But
    2.14
     entsprechende
    2.14
    Activations Density 0.003%

    No Known Activations