© 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-65K
    7. 5207
    Prev
    Next
    INDEX
    Explanations

    key elements

    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_65k_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
     can
    0.88
    e
    0.81
     be
    0.79
    ك
    0.77
    ۴
    0.77
    ق
    0.77
    ف
    0.75
    ני
    0.72
    لا
    0.72
    (
    0.71
    POSITIVE LOGITS
     elementos
    0.95
     éléments
    0.94
     компонен
    0.92
     élément
    0.92
     elementi
    0.87
     elemento
    0.86
    éléments
    0.85
     elementy
    0.84
     عناصر
    0.83
     элементов
    0.82
    Activations Density 0.096%

    No Known Activations