© 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. 286
    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
     ਹੈ
    0.86
     winged
    0.83
     Ө
    0.83
    čiai
    0.81
    жды
    0.80
    ťou
    0.80
    үү
    0.78
    тья
    0.77
     حسن
    0.77
     kurul
    0.77
    POSITIVE LOGITS
    dataloader
    1.05
     béton
    1.03
    িং
    0.98
    rendre
    0.96
    tric
    0.96
    拃
    0.91
     contenu
    0.91
     facilement
    0.90
     détect
    0.90
    énergie
    0.88
    Activations Density 0.000%

    No Known Activations