© 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. 9624
    Prev
    Next
    INDEX
    Explanations

    questions about your experience

    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
     Ако
    0.48
     è
    0.48
    のである
    0.46
     ако
    0.45
     хотим
    0.45
    敵人
    0.45
     хотят
    0.45
     защото
    0.45
    ੨
    0.44
     ถ้า
    0.44
    POSITIVE LOGITS
     your
    0.77
     yourself
    0.66
    你的
    0.55
    在你
    0.55
     vostri
    0.54
     Yourself
    0.53
    あなたの
    0.52
    your
    0.52
     ನಿಮ್ಮ
    0.50
     yourselves
    0.49
    Activations Density 0.158%

    No Known Activations