© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82790
    Prev
    Next
    INDEX
    Explanations

    generous and favorable qualities

    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
    ATUM
    -0.76
    不觉
    -0.75
     Cassini
    -0.75
     tornillos
    -0.75
    pertoire
    -0.73
    atório
    -0.73
    beautiful
    -0.73
    
    -0.73
    ldata
    -0.73
     vocale
    -0.72
    POSITIVE LOGITS
     generous
    3.61
     generously
    3.22
     charitable
    2.92
     generosity
    2.73
     Generous
    2.48
     optimistic
    2.31
    gener
    2.02
    optimis
    1.96
     großzü
    1.95
     optimis
    1.91
    Activations Density 0.033%

    No Known Activations