© 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. 10529
    Prev
    Next
    INDEX
    Explanations

    magazine URLs and code

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ædia
    0.85
     цикл
    0.84
    frist
    0.84
    シミ
    0.82
    λια
    0.81
     দেশকে
    0.79
    是一些
    0.79
    県
    0.79
    estan
    0.78
     стране
    0.77
    POSITIVE LOGITS
     Kearney
    1.10
     Kear
    0.98
     Delhi
    0.96
     Aye
    0.96
    Ar
    0.92
     Karm
    0.91
    Delhi
    0.91
    Kitchen
    0.91
     Kinn
    0.91
     দ
    0.91
    Activations Density 0.031%

    No Known Activations