© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11768
    Prev
    Next
    INDEX
    Explanations

    sql query clauses

    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_31_width_16k_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
    
    0.30
     voici
    0.30
     камен
    0.30
    写真は
    0.30
     saad
    0.29
     rmse
    0.28
    erende
    0.28
     convened
    0.27
     sauver
    0.27
    CTIONS
    0.27
    POSITIVE LOGITS
    之间
    0.31
    টিউট
    0.30
     buildup
    0.29
    叻
    0.29
    ඍ
    0.28
     thoroughly
    0.28
    䣼
    0.28
    ક્સ
    0.28
     foremost
    0.27
    치를
    0.27
    Activations Density 0.006%

    No Known Activations