© 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. 111014
    Prev
    Next
    INDEX
    Explanations

    imagination and creativity

    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
    charest
    -0.80
    מוד
    -0.78
    LookAnd
    -0.76
    WAUKEE
    -0.76
     आय
    -0.75
     اطلع
    -0.75
    Oy
    -0.75
     Empires
    -0.74
     olie
    -0.73
    verschluss
    -0.73
    POSITIVE LOGITS
     imagination
    5.09
    imagination
    3.80
     imaginations
    3.63
     Imagination
    3.59
     imaginative
    3.25
     imaginación
    3.25
    Imagin
    3.20
     imagin
    2.83
    imagin
    2.69
     Imagin
    2.61
    Activations Density 0.041%

    No Known Activations