© 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. 4072
    Prev
    Next
    INDEX
    Explanations

    well-being and health status

    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
     abnormalities
    1.04
    異常
    1.02
     disruptions
    1.02
    ध्व
    1.02
    АН
    1.01
    低于
    1.00
    巔
    0.98
    وح
    0.97
     disturbances
    0.97
     جاس
    0.96
    POSITIVE LOGITS
     sake
    1.03
     economy
    0.96
    ecology
    0.94
     ecology
    0.93
     Economy
    0.91
     நிச்சயம்
    0.90
     b
    0.90
     Ecology
    0.90
     Metab
    0.88
    umb
    0.88
    Activations Density 0.343%

    No Known Activations