© 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. 8516
    Prev
    Next
    INDEX
    Explanations

    afternoon (time)

    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
    migrations
    0.94
    ר
    0.91
    mert
    0.91
    rt
    0.91
    din
    0.89
    الأ
    0.89
    dump
    0.87
    י
    0.87
    ر
    0.86
    ก
    0.86
    POSITIVE LOGITS
     vores
    1.15
     unsere
    1.03
     NUS
    0.98
     leren
    0.98
     Suzanne
    0.98
     conosco
    0.97
     conna
    0.97
     utilisons
    0.97
     लेंगे
    0.97
     vegan
    0.96
    Activations Density 0.082%

    No Known Activations