© 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. 21844
    Prev
    Next
    INDEX
    Explanations

    record breaking

    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
     মন্
    0.40
     Feedback
    0.37
    му
    0.37
     Tad
    0.37
     upl
    0.37
    ݢ
    0.37
    苾
    0.37
    อป
    0.36
     Choices
    0.36
    嶺
    0.36
    POSITIVE LOGITS
     record
    2.34
     рекорд
    2.34
     rekord
    2.23
     récord
    2.14
    record
    2.13
     Record
    1.94
    Record
    1.88
     রেকর্ড
    1.84
     records
    1.80
    记录
    1.80
    Activations Density 0.031%

    No Known Activations