© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 79
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estrogens
    1.03
    ഹ്ലാദ
    1.03
    á
    1.02
     etiam
    1.00
     entro
    0.98
     inscri
    0.97
    ни
    0.95
     inaugur
    0.93
    นี่
    0.93
     bergabung
    0.93
    POSITIVE LOGITS
     물론
    1.23
     consulate
    1.04
     गौरतलब
    0.92
    প
    0.91
     pamoja
    0.90
    진다
    0.89
     এছাড়াও
    0.87
    嬅
    0.87
     conversational
    0.86
     false
    0.85
    Activations Density 0.381%

    No Known Activations