© 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. 8066
    Prev
    Next
    INDEX
    Explanations

    variable definitions followed by value

    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
     AdWords
    1.00
     Marcell
    0.87
     Liv
    0.84
    uzione
    0.81
     <?
    0.80
    Soap
    0.80
    Service
    0.79
     службу
    0.79
     मीडियम
    0.79
    バリー
    0.79
    POSITIVE LOGITS
     Southerners
    1.08
    ゴルフクラブ
    0.98
     recomb
    0.95
    JFrame
    0.94
     Swing
    0.94
    SwingConstants
    0.92
     loan
    0.92
     golfers
    0.92
    áj
    0.91
    蕉
    0.91
    Activations Density 0.007%

    No Known Activations