© 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. 8476
    Prev
    Next
    INDEX
    Explanations

    countries and their activities

    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
     proximate
    0.93
    ИК
    0.92
    fns
    0.88
    ണം
    0.87
    蔬
    0.87
    いま
    0.86
     katika
    0.85
     पड़ी
    0.83
     kwenye
    0.83
    اں
    0.81
    POSITIVE LOGITS
    scissors
    1.06
    Ges
    1.05
     çı
    1.03
     dequeue
    1.02
                  
    1.01
     Salvador
    0.98
    GES
    0.96
     GES
    0.96
    ∠
    0.95
    GB
    0.95
    Activations Density 0.000%

    No Known Activations