© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2619
    Prev
    Next
    INDEX
    Explanations

    Capital City UNESCO nominations

    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
     rendering
    -0.84
     erwerben
    -0.78
     znaczy
    -0.78
     Präsidenten
    -0.74
    multiline
    -0.74
    lifford
    -0.74
     llamada
    -0.73
     Statewide
    -0.73
    chus
    -0.72
     inaczej
    -0.72
    POSITIVE LOGITS
     Capital
    1.42
    Capital
    1.29
     CAPITAL
    1.23
     UNESCO
    1.09
     capitale
    1.09
    City
    1.08
     capital
    1.03
     City
    1.02
    capital
    1.02
     Unesco
    0.97
    Activations Density 0.008%

    No Known Activations