© 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. 33208
    Prev
    Next
    INDEX
    Explanations

    trades and contracts

    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
    ichtlich
    -0.91
    Performance
    -0.85
     \\
    
    -0.83
    予約
    -0.83
    ódio
    -0.82
    PERFORMANCE
    -0.82
     performance
    -0.81
    uação
    -0.81
    specialized
    -0.81
     Qaeda
    -0.81
    POSITIVE LOGITS
     suitors
    1.00
     available
    0.96
     salary
    0.95
     hypothetical
    0.94
    serialize
    0.89
     scenario
    0.87
     attractiveness
    0.85
     shopping
    0.84
    salary
    0.84
    Elephant
    0.84
    Activations Density 0.036%

    No Known Activations