© 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-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2937
    Prev
    Next
    INDEX
    Explanations

    locations and brands

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

    brand names

    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_53_width_65k_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
     \"
    0.44
     `${
    0.43
     ``
    0.41
     \...
    0.41
     menny
    0.40
     arbitrary
    0.39
     investigated
    0.38
     \,
    0.38
     homosexual
    0.38
     了
    0.37
    POSITIVE LOGITS
     Thrive
    0.75
     Pixel
    0.71
     Think
    0.70
     Beyond
    0.69
     Empower
    0.68
     Simply
    0.67
     Smart
    0.66
     Infinite
    0.66
     Quantum
    0.65
     Inspire
    0.64
    Activations Density 0.509%

    No Known Activations