© 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. 24-GEMMASCOPE-2-RES-16K
    7. 8466
    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_24_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
    ריך
    0.74
     forest
    0.71
     flo
    0.70
     forests
    0.69
    ↵
    0.68
     trim
    0.68
     clerk
    0.68
     стара
    0.65
     stopped
    0.64
    f
    0.64
    POSITIVE LOGITS
     Espanha
    0.95
     fomentar
    0.92
     Eğ
    0.92
    ENCIAS
    0.89
     étudier
    0.88
     Yönet
    0.84
     accéder
    0.84
     Estudos
    0.84
    юнча
    0.83
     Brésil
    0.83
    Activations Density 0.000%

    No Known Activations