© 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. 16-GEMMASCOPE-2-RES-262K
    7. 2085
    Prev
    Next
    INDEX
    Explanations

    self, micro, hyper prefixes

    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_16_width_262k_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
    م
    0.69
    ات
    0.64
    ين
    0.61
    en
    0.60
    س
    0.58
    其他
    0.57
    خ
    0.57
    ق
    0.56
    ح
    0.55
    in
    0.55
    POSITIVE LOGITS
    ulating
    0.39
    áról
    0.36
    leukin
    0.36
    ubes
    0.35
     صہیونیت
    0.35
     principalTable
    0.35
    认为是
    0.35
    পাতি
    0.35
    搡
    0.35
    neath
    0.33
    Activations Density 0.259%

    No Known Activations