© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13875
    Prev
    Next
    INDEX
    Explanations

    introducing separate items or components

    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_7_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
    Й
    1.89
    дцать
    1.78
    готов
    1.77
     piccole
    1.75
     milligrams
    1.72
    ゲ
    1.67
     jobs
    1.67
     leaflets
    1.67
    iglich
    1.67
     tds
    1.64
    POSITIVE LOGITS
    رى
    1.93
    ەکە
    1.89
    oq
    1.87
    에
    1.85
     χρη
    1.84
    anud
    1.84
    ੀ
    1.84
    هان
    1.81
    aun
    1.78
    ený
    1.75
    Activations Density 0.000%

    No Known Activations