© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10965
    Prev
    Next
    INDEX
    Explanations

    January 6th, org

    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
    
    1.07
    Obama
    1.04
     Clooney
    1.03
     Huffington
    1.01
     Obama
    1.00
     Crocker
    1.00
     iPod
    1.00
    巧克力
    0.99
    érale
    0.98
     Schwarzenegger
    0.98
    POSITIVE LOGITS
     Joe
    1.22
    🤍
    1.21
    Joe
    1.21
    🫶
    1.21
    🩷
    1.20
    joe
    1.16
     joe
    1.14
    🫡
    1.10
    🟦
    1.07
     Biden
    1.07
    Activations Density 0.090%

    No Known Activations