© 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-16K
    7. 13866
    Prev
    Next
    INDEX
    Explanations

    product title

    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
     b
    0.39
     Bak
    0.37
    க்கூட
    0.35
     lr
    0.34
     h
    0.34
     Physic
    0.33
     um
    0.33
     ram
    0.33
     mane
    0.32
     probable
    0.32
    POSITIVE LOGITS
    橑
    0.42
    становка
    0.41
    まさに
    0.41
     সত্যিকার
    0.40
     الأخرى
    0.39
    ᴙ
    0.39
    创意
    0.39
    再び
    0.38
     నిజ
    0.38
     gerçekten
    0.38
    Activations Density 0.363%

    No Known Activations