© 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-65K
    7. 19689
    Prev
    Next
    INDEX
    Explanations

    chat and socket connections

    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_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
    依法
    0.43
     distillate
    0.43
     ঘণ্টা
    0.41
    🐚
    0.41
     ชั่วโมง
    0.40
    蒸
    0.40
    𝓎
    0.39
    股份有限公司
    0.38
    hourglass
    0.38
     огра
    0.38
    POSITIVE LOGITS
     naam
    0.38
     två
    0.38
     phòng
    0.37
     sylvis
    0.37
     Lub
    0.37
     namens
    0.37
                                
    0.37
     WOL
    0.37
     Midwest
    0.36
     Kirchner
    0.36
    Activations Density 0.052%

    No Known Activations