© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 64897
    Prev
    Next
    INDEX
    Explanations

    Turkey, water, header, corrosive

    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
     மிரு
    0.42
     racional
    0.41
    𝑙
    0.40
     ล
    0.38
    也不
    0.38
    illation
    0.38
    ਾਨ
    0.38
    
    0.38
     overturn
    0.37
     feminino
    0.37
    POSITIVE LOGITS
    跑
    0.40
     suono
    0.39
    첸
    0.39
     решать
    0.39
     الوضع
    0.38
    LIKE
    0.38
    Image
    0.37
    ಗದ
    0.36
    Form
    0.36
     Mitglieder
    0.36
    Activations Density 0.001%

    No Known Activations