© 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-16K
    7. 9113
    Prev
    Next
    INDEX
    Explanations

    assembly and code

    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_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
     Investors
    0.41
    BoolVar
    0.39
    멍
    0.37
     прис
    0.37
     Owners
    0.37
    Borrowed
    0.36
     tempData
    0.36
     بالط
    0.36
    誼
    0.36
    鄉
    0.35
    POSITIVE LOGITS
     asm
    0.73
    asm
    0.71
     syscall
    0.71
    syscall
    0.70
     ASM
    0.63
    Elf
    0.61
     address
    0.59
     addresses
    0.59
     ELF
    0.59
     Elf
    0.57
    Activations Density 0.110%

    No Known Activations