© 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. 298
    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
    ה
    1.07
    ی
    1.06
    a
    0.99
    ر
    0.96
    ت
    0.95
    र
    0.93
    ר
    0.85
    t
    0.79
    م
    0.79
    e
    0.79
    POSITIVE LOGITS
     eben
    0.80
    ☠
    0.75
    OSS
    0.75
     ребят
    0.73
    ഷേധ
    0.71
    OPES
    0.70
     Energies
    0.69
     internacionales
    0.68
    DropdownBox
    0.67
    0.67
    Activations Density 0.152%

    No Known Activations