© 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. 20946
    Prev
    Next
    INDEX
    Explanations

    updates and discussions

    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
     बोले
    0.46
     बोलेंगे
    0.43
    務
    0.39
    Counc
    0.38
    >/</
    0.37
     الاشت
    0.36
    neys
    0.36
     গুলি
    0.36
    ُر
    0.36
    ！）
    0.36
    POSITIVE LOGITS
    ක්
    0.56
     introductions
    0.55
     sevgili
    0.52
    isième
    0.50
    arriv
    0.49
     kekurangan
    0.48
     símbolo
    0.48
     colloc
    0.48
     initiation
    0.48
    leftharpoons
    0.48
    Activations Density 0.012%

    No Known Activations