© 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-16K
    7. 2016
    Prev
    Next
    INDEX
    Explanations

    option

    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_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
    0.41
     clothes
    0.34
     vegetables
    0.31
    ↵
    0.31
     words
    0.31
     hair
    0.30
     music
    0.29
     lettuce
    0.29
     beer
    0.28
     grammar
    0.28
    POSITIVE LOGITS
     ወቅ
    0.33
    ק
    0.32
     вариан
    0.31
     приорите
    0.31
     તેમજ
    0.29
     Стаўкі
    0.29
     устойчи
    0.29
    Depending
    0.28
     варианты
    0.28
    इका
    0.28
    Activations Density 1.155%

    No Known Activations