© 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. 535
    Prev
    Next
    INDEX
    Explanations

    **Mus, mu, and similar sounds/names**

    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
     polarizing
    0.45
     rost
    0.45
     possibile
    0.45
     Listings
    0.45
     ballistic
    0.44
    یان
    0.44
    붐
    0.44
     suffices
    0.43
     repel
    0.43
     bunların
    0.43
    POSITIVE LOGITS
     म्यू
    0.69
    Mus
    0.68
    achio
    0.61
    穆
    0.61
    hammad
    0.60
    ammad
    0.60
    herjee
    0.60
    ніципа
    0.58
    ñoz
    0.57
     Му
    0.57
    Activations Density 0.116%

    No Known Activations