© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8878
    Prev
    Next
    INDEX
    Explanations

    why did joke setups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    primarily
    0.76
     Otherwise
    0.76
     otherwise
    0.75
    టర్‌
    0.71
    </h3>
    0.71
     (
    0.71
     OTHERWISE
    0.70
     Zeit
    0.67
    zust
    0.66
     discernible
    0.66
    POSITIVE LOGITS
    <unused1463>
    1.08
     amazed
    1.05
     pelea
    1.04
    DanhMucSP
    1.03
     insanely
    1.02
     stupid
    1.02
    pleClass
    1.01
     rookie
    1.01
     veterin
    1.01
    <unused1391>
    1.00
    Activations Density 0.036%

    No Known Activations