© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 2587
    Prev
    Next
    INDEX
    Explanations

    retarded offensive term

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
     pinMode
    0.48
    Fmat
    0.46
     ჩატი
    0.45
    ostar
    0.45
    <unused5>
    0.44
    стройки
    0.44
    䣫
    0.43
    も含
    0.42
     맨
    0.42
    ទំនាក់
    0.42
    POSITIVE LOGITS
     bracelet
    0.43
     je
    0.40
     pra
    0.40
     verdade
    0.40
     interessante
    0.40
    </code>
    0.39
    ardust
    0.39
    受
    0.39
     Bracelet
    0.38
    <unused61>
    0.38
    Activations Density 0.007%

    No Known Activations