© 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. 347
    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
     성
    0.64
     원
    0.58
     점
    0.57
     비
    0.57
     신
    0.57
    водит
    0.57
     파
    0.57
     成
    0.56
     광
    0.56
     통
    0.56
    POSITIVE LOGITS
     neste
    0.48
     doma
    0.48
     dacă
    0.47
     zbog
    0.47
     pada
    0.46
     nesta
    0.44
     stale
    0.43
     spust
    0.43
     sama
    0.43
     kalau
    0.42
    Activations Density 0.224%

    No Known Activations