© 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. 58803
    Prev
    Next
    INDEX
    Explanations

    for-profit and non-profit structures

    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
     realistic
    -0.73
    lation
    -0.71
    ļas
    -0.70
    veness
    -0.70
     bright
    -0.69
    ξύ
    -0.68
    Contd
    -0.68
    iarkan
    -0.64
    atians
    -0.64
    camiento
    -0.64
    POSITIVE LOGITS
     profit
    3.02
     nonprofit
    2.67
    profit
    2.63
    Profit
    2.47
     Profit
    2.36
     Nonprofit
    2.00
     profits
    1.96
     nonprofits
    1.77
    profits
    1.56
     Profits
    1.51
    Activations Density 0.042%

    No Known Activations