© 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. 31-GEMMASCOPE-2-RES-65K
    7. 31018
    Prev
    Next
    INDEX
    Explanations

    understand sanitation composition learned

    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
    ли
    0.47
     thuốc
    0.38
     Governo
    0.37
     нагрузки
    0.37
    ိ
    0.37
    各类
    0.36
     bác
    0.36
     parcels
    0.36
     senc
    0.35
    집
    0.35
    POSITIVE LOGITS
    ៖
    0.47
    ភាព
    0.45
     afgelopen
    0.43
    iteit
    0.42
    uates
    0.41
     "&#
    0.41
    蛻
    0.41
     unisex
    0.41
    íssimo
    0.40
    ︰
    0.40
    Activations Density 0.001%

    No Known Activations