© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 29249
    Prev
    Next
    INDEX
    Explanations

    new and followed by `;` or `=`

    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_262k_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
     яке
    0.43
     которое
    0.43
     मिळाली
    0.41
     बताती
    0.40
    ☪
    0.39
    
    0.38
     ઘણી
    0.37
     उतनी
    0.36
    zott
    0.36
    Œ
    0.36
    POSITIVE LOGITS
     new
    1.10
     নতুন
    0.88
     nuevos
    0.87
    新的
    0.87
     nuova
    0.87
     nuove
    0.86
     नए
    0.83
     नया
    0.83
     neuen
    0.83
    new
    0.82
    Activations Density 0.002%

    No Known Activations