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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1179
    Prev
    Next
    INDEX
    Explanations

    innovation and creativity

    np_acts-logits-general · gemini-2.5-flash-lite

    creativity and innovation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grumpy
    0.49
     massacre
    0.48
     badminton
    0.46
     granularity
    0.46
     glacial
    0.45
     विंड
    0.45
     कुंडली
    0.45
    た
    0.44
     mahogany
    0.43
     grudge
    0.42
    POSITIVE LOGITS
     creativity
    1.18
     creatividad
    1.10
    创新
    1.09
     Creativity
    1.02
     creativa
    1.02
     innovators
    1.00
     kreativ
    1.00
    innov
    0.97
     creatively
    0.95
    創意
    0.95
    Activations Density 0.209%

    No Known Activations