© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 238
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_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
    éditeur
    0.96
     Seguridad
    0.93
    嘜
    0.93
     révé
    0.91
     प्रोड
    0.91
     خبرگزاری
    0.91
    编译器
    0.90
    JlcG
    0.90
    谥
    0.88
     działania
    0.87
    POSITIVE LOGITS
     people
    2.87
     patients
    2.84
     individuals
    2.71
     students
    2.54
     persons
    2.52
     users
    2.51
     customers
    2.48
     residents
    2.47
     citizens
    2.41
    people
    2.39
    Activations Density 9.675%

    No Known Activations