© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 3791
    Prev
    Next
    INDEX
    Explanations

    last word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ärer
    0.40
     পড়তে
    0.40
    趣
    0.39
     suav
    0.39
     Footage
    0.38
     فضای
    0.38
    
    0.38
    さらに
    0.37
    —
    0.37
    
    0.37
    POSITIVE LOGITS
     Last
    0.88
     آخرین
    0.80
    last
    0.79
     LAST
    0.79
     last
    0.77
    Last
    0.75
     आखिरी
    0.73
     getLast
    0.73
     最後
    0.72
     लास्ट
    0.71
    Activations Density 0.054%

    No Known Activations