© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13940
    Prev
    Next
    INDEX
    Explanations

    open-minded sensor day

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

    enabling users

    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_16k_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
    陈
    0.43
     serene
    0.40
     unfortunate
    0.40
    我们会
    0.40
     prosperous
    0.40
    谨慎
    0.38
     :
    0.37
    jà
    0.37
     rất
    0.37
    0.37
    POSITIVE LOGITS
     মুক্তিবাহিনীর
    0.48
     গেরিলারা
    0.47
     গেরিলাদের
    0.47
     proporciona
    0.46
    riculum
    0.46
     आवासीय
    0.45
     মুক্তিব
    0.45
     proporcionan
    0.44
     പ്രവർത്തന
    0.43
    ವಲ್ಲ
    0.43
    Activations Density 0.458%

    No Known Activations