© 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. 18163
    Prev
    Next
    INDEX
    Explanations

    ignorance

    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
    تو
    1.00
    تن
    0.97
    Дру
    0.94
    گ
    0.94
    נ
    0.93
    ای
    0.89
    مت
    0.89
    Лю
    0.89
    Пе
    0.88
    Від
    0.88
    POSITIVE LOGITS
    ignor
    1.12
     ignorance
    1.09
     ignorant
    0.95
     unaware
    0.74
     uninformed
    0.74
    0
    0.73
     Ign
    0.72
    awareness
    0.71
    learning
    0.70
    feeling
    0.70
    Activations Density 0.002%

    No Known Activations