© 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. 62566
    Prev
    Next
    INDEX
    Explanations

    hooves

    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
    提案
    0.38
     خلق
    0.38
    活用
    0.38
     neck
    0.38
     itemscope
    0.37
    انیه
    0.37
    чва
    0.36
    န်
    0.36
    ు
    0.35
    proposed
    0.35
    POSITIVE LOGITS
     shoe
    0.89
     Shoe
    0.82
    shoe
    0.79
     shoes
    0.78
     Shoes
    0.77
    shoes
    0.75
    Shoes
    0.71
    鞋
    0.61
     Sho
    0.60
     鞋
    0.59
    Activations Density 0.004%

    No Known Activations