© 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. 127556
    Prev
    Next
    INDEX
    Explanations

    acrylamide gels or Cunningham

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

    The neuron detects last names, particularly "Cunningham," and technical biochemistry terms like "acrylamide" and "polyacrylamide."

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Not in Any Lists

    No Comments

    Negative Logits
    2
    -3.17
    3
    -3.00
    4
    -2.78
    　　　　
    -2.64
    　　　　　　
    -2.59
    　　　　　
    -2.55
    5
    -2.53
    1
    -2.53
    　　　
    -2.50
    7
    -2.31
    POSITIVE LOGITS
     letzten
    2.67
     That
    2.66
     Those
    2.56
    釆
    2.55
     For
    2.55
     Thankfully
    2.52
     Until
    2.42
     Their
    2.41
     Nevertheless
    2.41
    lgari
    2.39
    Activations Density 0.004%

    No Known Activations