© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5587
    Prev
    Next
    INDEX
    Explanations

    captivating that took

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-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
     avoid
    0.75
     tránh
    0.72
     disliked
    0.70
     avoids
    0.70
    晗
    0.70
     evitar
    0.69
     avoided
    0.66
     obviamente
    0.66
     :(
    0.66
     criticized
    0.64
    POSITIVE LOGITS
     fascinating
    1.01
     enchanting
    0.97
     unforgettable
    0.93
     captivating
    0.93
     fascination
    0.92
     Treasures
    0.91
     extraordinary
    0.90
    Adventure
    0.89
     remarkable
    0.88
     Adventure
    0.88
    Activations Density 0.274%

    No Known Activations