© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6604
    Prev
    Next
    INDEX
    Explanations

    assigned male at birth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    říklad
    0.69
    స్తున్నాయి
    0.67
    小型
    0.66
    evším
    0.66
    effectuer
    0.66
    爣
    0.66
     আসবেন
    0.64
    न्ग
    0.64
    きます
    0.63
    大规模
    0.63
    POSITIVE LOGITS
    했고
    1.00
     and
    0.98
    そして
    0.98
     そして
    0.98
     but
    0.94
     и
    0.91
     și
    0.91
     וה
    0.91
     وكانت
    0.88
     এবং
    0.87
    Activations Density 0.033%

    No Known Activations