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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10762
    Prev
    Next
    INDEX
    Explanations

    C# code structures

    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
    stoke
    0.88
     watch
    0.86
    vah
    0.86
    чай
    0.85
    嗆
    0.84
    ವಾಗ
    0.83
    খ্য
    0.83
    !]
    0.82
    </sup>
    0.82
    boh
    0.81
    POSITIVE LOGITS
    さんは
    0.96
     diadakan
    0.94
     xong
    0.93
    さんの
    0.93
     сохра
    0.91
    iseconds
    0.91
     поднима
    0.91
     دولار
    0.90
    さんに
    0.90
     установи
    0.89
    Activations Density 0.004%

    No Known Activations