© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 32043
    Prev
    Next
    INDEX
    Explanations

    can, just, without

    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_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
    pinned
    0.40
     refuses
    0.39
     alcoholism
    0.39
    štu
    0.39
     actor
    0.38
     supplies
    0.38
     Ni
    0.36
     니
    0.36
    Stat
    0.35
     Tar
    0.35
    POSITIVE LOGITS
     epoca
    0.55
    Очень
    0.50
    時刻
    0.50
    ลักษณะ
    0.49
    ସ
    0.49
    Ве
    0.47
    कालिक
    0.47
     கண்கா
    0.47
    чора
    0.47
    ंबकीय
    0.46
    Activations Density 0.003%

    No Known Activations