© 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. 332
    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
     กิน
    1.08
     प्रशंसकों
    1.03
    观测
    1.03
     leeft
    1.01
     potrav
    1.00
    嫔
    1.00
    Jogador
    1.00
    กิน
    0.97
    馒
    0.95
     obserw
    0.95
    POSITIVE LOGITS
     services
    2.13
     Services
    1.96
    services
    1.82
    Services
    1.82
     услуги
    1.82
     service
    1.78
     SERVICES
    1.76
     услу
    1.69
     услуг
    1.69
     outsourcing
    1.66
    Activations Density 7.849%

    No Known Activations