© 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. 340
    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
     показателей
    1.06
     размеров
    1.03
     mecz
    1.03
     résultats
    0.98
     vhod
    0.96
     ошибок
    0.95
     nauczyc
    0.94
    ờ
    0.94
     paździer
    0.93
     chercheurs
    0.92
    POSITIVE LOGITS
     community
    2.04
     ecosystem
    2.00
     universe
    1.92
     realm
    1.74
     society
    1.72
     workforce
    1.69
     sector
    1.67
     group
    1.63
     population
    1.61
     sphere
    1.61
    Activations Density 8.909%

    No Known Activations