© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 27922
    Prev
    Next
    INDEX
    Explanations

    "Madam, I'm Adam"

    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/layer_40_width_262k_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
     коже
    0.41
     পাশ্চাত্য
    0.41
    culos
    0.41
     locationManager
    0.41
    ɻ
    0.39
    द्योग
    0.38
     nữ
    0.38
    स्ड
    0.38
     jovem
    0.38
     සිය
    0.38
    POSITIVE LOGITS
     off
    0.41
    捙
    0.40
     von
    0.40
     No
    0.40
     ваш
    0.39
     ваши
    0.39
     ஒ
    0.38
     going
    0.37
     nhờ
    0.37
     عبارت
    0.37
    Activations Density 0.000%

    No Known Activations