© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9220
    Prev
    Next
    INDEX
    Explanations

    function return descriptions

    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
     höch
    0.93
     Convert
    0.93
    #!
    0.90
    ryption
    0.89
     entfernt
    0.87
     rund
    0.86
    \\\
    0.86
    ijer
    0.86
    рор
    0.86
     дизайне
    0.83
    POSITIVE LOGITS
    entlichen
    0.84
    就被
    0.84
     taxing
    0.83
     commodities
    0.82
    وصل
    0.82
    引
    0.82
    sty
    0.80
    িল্ল
    0.79
    ਨੀ
    0.78
     विभक्ति
    0.78
    Activations Density 0.008%

    No Known Activations