© 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. 766
    Prev
    Next
    INDEX
    Explanations

    returning results or values

    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
    d
    2.28
    ↵↵
    2.05
    m
    1.98
    em
    1.85
    erv
    1.84
    r
    1.83
    ro
    1.78
    etc
    1.78
    ero
    1.75
    Free
    1.75
    POSITIVE LOGITS
     能
    2.50
     实现
    2.47
     连接
    2.34
     其中
    2.34
     功能
    2.29
     组件
    2.29
     grantResults
    2.26
     作为
    2.25
     coupler
    2.24
     啊
    2.21
    Activations Density 0.966%

    No Known Activations