© 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. 87811
    Prev
    Next
    INDEX
    Explanations

    India, PTI, percent, home, AYUSH

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

    discussing what is not allowed

    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
    𝗸
    0.54
    𝙙
    0.52
     ESTIM
    0.52
    𝘴
    0.52
    %/
    0.50
     choke
    0.50
    বিমান
    0.50
    ުރ
    0.49
     ನನಗೆ
    0.49
    bandwidth
    0.48
    POSITIVE LOGITS
     Commandant
    0.50
     Forces
    0.50
    ']):
    0.47
     draftsman
    0.47
     Sheets
    0.45
     paredes
    0.45
     Liberties
    0.45
     независимо
    0.44
     Cristal
    0.44
     Stanford
    0.44
    Activations Density 0.001%

    No Known Activations