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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7833
    Prev
    Next
    INDEX
    Explanations

    including or inclusive

    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
    微微
    0.86
    遐
    0.86
    頑張
    0.83
    ιτε
    0.83
    偽
    0.80
    ரமாக
    0.79
    辯
    0.78
    ärast
    0.78
     consequ
    0.77
    侃
    0.76
    POSITIVE LOGITS
     included
    4.33
    included
    4.08
     Included
    3.92
     inclu
    3.87
     inclusion
    3.85
     include
    3.79
    include
    3.72
    Included
    3.70
     includes
    3.62
     inclus
    3.60
    Activations Density 0.440%

    No Known Activations