© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8678
    Prev
    Next
    INDEX
    Explanations

    psychology, neuroscience, TED talks

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

    Eisenhower matrix and productivity

    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
     perj
    0.49
     quedan
    0.49
     papeles
    0.48
     cylindrical
    0.46
     vols
    0.46
    mdi
    0.45
     improper
    0.44
    纖
    0.43
     valorem
    0.43
     mpl
    0.42
    POSITIVE LOGITS
     Mindfulness
    1.00
     TED
    0.99
     Psychologist
    0.98
     neuroscience
    0.95
     Psychology
    0.93
     psychologist
    0.93
     McKinsey
    0.93
     mindfulness
    0.92
    TED
    0.89
     psychology
    0.88
    Activations Density 0.207%

    No Known Activations