© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 56703
    Prev
    Next
    INDEX
    Explanations

    random forest

    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
    Negative Logits
    random
    0.48
     //[
    0.41
     random
    0.40
     boston
    0.40
     libsql
    0.39
    InfoPlist
    0.38
     স্বচ্ছ
    0.38
     orientación
    0.38
     направления
    0.37
     orientado
    0.37
    POSITIVE LOGITS
    forest
    0.40
    ghed
    0.40
     프랑
    0.37
     Finance
    0.37
    ഋ
    0.36
     snee
    0.35
    ange
    0.35
    нее
    0.35
    hane
    0.35
    Forest
    0.35
    Activations Density 0.001%

    No Known Activations