© 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. 13-GEMMASCOPE-2-RES-16K
    7. 6903
    Prev
    Next
    INDEX
    Explanations

    skin cancer, Johnson & Johnson, suffering

    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_13_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
     addObject
    1.04
     এক্ষেত্রে
    0.97
    ylamine
    0.93
     ਆਪਣੇ
    0.92
    部分的
    0.92
     앞
    0.91
     neto
    0.87
    facet
    0.86
    項
    0.85
     override
    0.85
    POSITIVE LOGITS
     ฟ้า
    1.19
    เพราะ
    1.07
     kami
    1.07
     somos
    1.06
    เรา
    1.03
    Blessed
    1.02
    Somos
    1.02
    Variety
    1.01
    Sono
    1.01
     inquiries
    1.00
    Activations Density 0.003%

    No Known Activations