© 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. 7951
    Prev
    Next
    INDEX
    Explanations

    plan, guide, menu, agenda, manual

    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
     kinematic
    0.44
     geometrical
    0.43
     eux
    0.42
    ائدة
    0.41
    ួ
    0.41
    فت
    0.40
     smoothness
    0.40
     saluran
    0.39
    حل
    0.39
    اء
    0.39
    POSITIVE LOGITS
     PDF
    0.55
     공유
    0.49
    లోని
    0.48
     작성
    0.48
     Sheet
    0.46
    PDF
    0.46
     PDFs
    0.45
     Entries
    0.44
    다
    0.44
    Pdf
    0.44
    Activations Density 0.012%

    No Known Activations