© 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. 12081
    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
    е
    0.91
    не
    0.87
     отличие
    0.87
    НИ
    0.80
     поводу
    0.78
    но
    0.74
    неш
    0.74
    г
    0.72
    э
    0.71
    expectation
    0.71
    POSITIVE LOGITS
     animale
    0.87
     carpeta
    0.83
     Susana
    0.77
    もしくは
    0.77
    哺乳
    0.77
     aiuta
    0.76
    体操
    0.75
    acqua
    0.73
     fels
    0.73
     construye
    0.73
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.