© 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. 41-GEMMASCOPE-2-RES-262K
    7. 34483
    Prev
    Next
    INDEX
    Explanations

    Notre Dame

    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
    вшейся
    0.42
    ήθ
    0.40
     confirma
    0.40
    ত্তা
    0.40
     oven
    0.39
     обычной
    0.39
    aparikkh
    0.38
    䏹
    0.38
    व्यू
    0.37
     пери
    0.37
    POSITIVE LOGITS
     Notre
    1.48
    Notre
    1.38
     ND
    0.83
    ND
    0.76
     Irish
    0.60
     irish
    0.60
     NDP
    0.59
     Fighting
    0.57
    Irish
    0.55
     nd
    0.54
    Activations Density 0.000%

    No Known Activations