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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60329
    Prev
    Next
    INDEX
    Explanations

    philately stamps USPS

    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
     promotions
    -0.77
     assets
    -0.77
     technologies
    -0.74
    uelo
    -0.74
    tillos
    -0.73
     constitucional
    -0.73
    conci
    -0.73
     game
    -0.72
     violence
    -0.71
     alloy
    -0.71
    POSITIVE LOGITS
     phil
    1.49
    phil
    1.27
    Phil
    1.00
     Phil
    1.00
     Postmaster
    0.98
     USPS
    0.91
    PHIL
    0.89
    postal
    0.83
     cliché
    0.83
     CTO
    0.82
    Activations Density 0.016%

    No Known Activations