© 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. 9578
    Prev
    Next
    INDEX
    Explanations

    breakdown of

    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
    ljanje
    0.89
    gers
    0.87
     هاکي
    0.87
     derivados
    0.86
     Blackmore
    0.85
     Landon
    0.85
     возникновения
    0.85
    Ᏻ
    0.84
    ब्दिक
    0.83
     Levine
    0.83
    POSITIVE LOGITS
     class
    2.10
    class
    1.82
     Class
    1.64
     classe
    1.57
    Class
    1.55
    klasse
    1.54
     clase
    1.51
     kelas
    1.48
    クラス
    1.48
     ক্লাস
    1.40
    Activations Density 0.090%

    No Known Activations