© 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. 40-GEMMASCOPE-2-RES-262K
    7. 4236
    Prev
    Next
    INDEX
    Explanations

    list item numbering

    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_40_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
     demás
    0.35
    ﺗ
    0.35
    पणा
    0.35
    మని
    0.34
     flotte
    0.34
     paragraphe
    0.34
    কালে
    0.34
     baud
    0.33
     altri
    0.33
     পদ্ধতির
    0.33
    POSITIVE LOGITS
    ️⃣
    0.71
    ⃣
    0.57
    :
    0.50
    ของการ
    0.50
    ′
    0.48
    ″
    0.47
     của
    0.41
    ের
    0.40
    :"
    0.39
    nd
    0.38
    Activations Density 0.092%

    No Known Activations