© 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. 106153
    Prev
    Next
    INDEX
    Explanations

    server names and DNS

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

    The neuron detects numeric tokens (sequences of digits), especially those in IP addresses, port numbers, and other technical numeric values.

    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
     Scrabble
    -0.82
    ASD
    -0.77
    ifr
    -0.75
     ACR
    -0.75
     backlash
    -0.72
     aix
    -0.72
     norman
    -0.69
    SUMMARY
    -0.69
    VET
    -0.68
     إدارة
    -0.68
    POSITIVE LOGITS
     DNS
    1.24
     Google
    1.15
     google
    1.01
    DNS
    0.96
     primary
    0.94
     Goo
    0.90
    google
    0.88
     public
    0.84
     fastest
    0.82
    alternate
    0.82
    Activations Density 0.022%

    No Known Activations