© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46595
    Prev
    Next
    INDEX
    Explanations

    explaining projects, javascript, arguments, and conditions

    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
    ченный
    0.46
    ¸
    0.46
    σταση
    0.43
    ፎ
    0.39
     செய்யப்பட்ட
    0.39
    დნენ
    0.39
     individuales
    0.38
     spt
    0.38
     izquier
    0.37
    ised
    0.37
    POSITIVE LOGITS
    अपना
    0.52
     year
    0.48
     one
    0.47
    ８
    0.47
     to
    0.47
    １
    0.46
    amah
    0.45
     Presidential
    0.44
    उ
    0.44
     বাড়ছে
    0.44
    Activations Density 0.007%

    No Known Activations