© 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. 106113
    Prev
    Next
    INDEX
    Explanations

    internet connection lines

    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
    Negative Logits
    🔘
    -0.88
    Oui
    -0.84
    getUsers
    -0.82
     penderita
    -0.78
    Luft
    -0.76
     arbre
    -0.75
     pongo
    -0.75
     meurt
    -0.75
    宙
    -0.73
    WeChat
    -0.72
    POSITIVE LOGITS
     connection
    4.00
     connections
    3.39
    connection
    3.08
    Connection
    2.73
     Connection
    2.72
    connections
    2.47
     Connections
    2.38
     lines
    2.28
    CONNECTION
    2.27
     line
    2.25
    Activations Density 0.081%

    No Known Activations