© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 694
    Prev
    Next
    INDEX
    Explanations

    information about learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     Zionist
    0.87
     prohib
    0.85
     Scot
    0.83
     Ramsay
    0.83
    iffen
    0.81
    ümler
    0.78
     Yogi
    0.78
    <0x89>
    0.78
     presum
    0.77
    aturing
    0.76
    POSITIVE LOGITS
     satisfait
    1.15
    รัก
    1.10
    KAT
    1.10
     memnun
    1.08
     elog
    1.08
     дово
    1.08
    love
    1.07
     satis
    1.07
     praise
    1.07
     piaci
    1.06
    Activations Density 3.195%

    No Known Activations