© 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. 106463
    Prev
    Next
    INDEX
    Explanations

    airport gates

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Not in Any Lists

    No Comments

    Negative Logits
     ATV
    -0.93
     Commodore
    -0.87
     Jamestown
    -0.84
     loaned
    -0.84
    demik
    -0.83
     Retailers
    -0.83
     trance
    -0.82
     GSH
    -0.82
     scrimmage
    -0.82
     outfield
    -0.82
    POSITIVE LOGITS
     gate
    1.48
    Gate
    1.31
     Gate
    1.29
     gates
    1.11
    gate
    1.10
     Alleg
    1.02
     Salt
    0.95
     Delta
    0.91
     hubs
    0.89
     Gates
    0.87
    Activations Density 0.049%

    No Known Activations