© 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. 7468
    Prev
    Next
    INDEX
    Explanations

    last past recent time

    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
     используются
    0.46
     используется
    0.44
     এইরূপ
    0.40
    到一个
    0.40
    将在
    0.40
     Decade
    0.39
     যদি
    0.39
    ፑ
    0.39
     문제는
    0.39
     decade
    0.38
    POSITIVE LOGITS
     afgelopen
    0.95
     scorso
    0.91
     scorsa
    0.90
     vorige
    0.88
     kemarin
    0.87
    昨年
    0.82
     last
    0.82
    上次
    0.82
    去年
    0.81
     지난
    0.79
    Activations Density 0.114%

    No Known Activations