© 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. 41-GEMMASCOPE-2-RES-262K
    7. 62220
    Prev
    Next
    INDEX
    Explanations

    patterns and lists

    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_all/layer_41_width_262k_l0_big
    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
    ற்றி
    0.39
    ourage
    0.38
    켈
    0.38
    ribusi
    0.37
    CER
    0.37
     pati
    0.36
     Kernel
    0.36
     paž
    0.35
    illon
    0.35
     Kerk
    0.35
    POSITIVE LOGITS
    Py
    0.51
    搡
    0.47
     Py
    0.45
     intensification
    0.41
     Intersection
    0.40
     Cun
    0.38
     প্রতিরক্ষা
    0.38
     দ্রব্য
    0.38
    వీ
    0.37
     automation
    0.37
    Activations Density 0.004%

    No Known Activations