© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64418
    Prev
    Next
    INDEX
    Explanations

    government planning and policy

    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
    🎺
    -0.79
     Amad
    -0.77
     indoor
    -0.73
     两
    -0.72
     вси
    -0.70
    joner
    -0.69
    Prze
    -0.69
    讒
    -0.69
     decisão
    -0.68
     scorched
    -0.68
    POSITIVE LOGITS
     CEO
    0.96
     Mission
    0.93
     кре
    0.86
     cellules
    0.86
    cell
    0.85
     Planning
    0.83
     Yor
    0.83
    mission
    0.81
     Prophets
    0.80
     mission
    0.79
    Activations Density 0.008%

    No Known Activations