© 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. 37706
    Prev
    Next
    INDEX
    Explanations

    about.com guide

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

    how to become a fiction writer

    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
    scrape
    0.44
     jouw
    0.43
     scrapes
    0.43
     ಉತ್ಪನ್ನ
    0.42
    ೆಯಲ್ಲಿ
    0.42
    '){
    0.41
    निटी
    0.41
    ুল্য
    0.41
    '])){
    0.41
    жны
    0.40
    POSITIVE LOGITS
     about
    0.47
     Lyme
    0.44
     About
    0.43
     much
    0.43
     бывшего
    0.41
     формат
    0.40
     Anger
    0.40
     word
    0.39
    About
    0.39
     leadership
    0.38
    Activations Density 0.014%

    No Known Activations