© 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. 47131
    Prev
    Next
    INDEX
    Explanations

    mailing list subscription

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

    The neuron detects invitations or requests to join or leave an email/mailing list.

    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
     knuckle
    -0.87
     represen
    -0.79
    港
    -0.78
     manufac
    -0.75
     knuckles
    -0.74
     Citations
    -0.73
     Hinge
    -0.73
    setCharacter
    -0.72
     bürger
    -0.72
    urnal
    -0.69
    POSITIVE LOGITS
     mailing
    3.27
     list
    2.56
     lists
    2.22
    Mailing
    2.20
     distribution
    2.17
    mailing
    2.16
     database
    2.11
     List
    2.02
     Mailing
    1.93
    List
    1.84
    Activations Density 0.035%

    No Known Activations