© 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. 13-GEMMASCOPE-2-RES-16K
    7. 2247
    Prev
    Next
    INDEX
    Explanations

    creative ways of understanding

    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
     retrieve
    1.96
     amminist
    1.78
     horse
    1.77
    ζα
    1.76
    Horse
    1.73
    вчи
    1.71
    
    1.69
    চন
    1.69
    Dado
    1.69
     दबा
    1.68
    POSITIVE LOGITS
    <bos>
    1.92
     Ceremon
    1.83
    tum
    1.74
     Ceremony
    1.73
    娶
    1.72
    tra
    1.71
     ceremony
    1.70
     ceremonies
    1.68
     결혼
    1.67
    ścic
    1.64
    Activations Density 0.369%

    No Known Activations