© 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. 9459
    Prev
    Next
    INDEX
    Explanations

    Adam or Adams

    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
    മ്പോള്‍
    0.49
    BATCH
    0.46
    ୟ
    0.46
    revalidator
    0.46
    ygons
    0.45
    rocessing
    0.45
    㷌
    0.45
    𝒙
    0.45
    ジュアル
    0.44
    ಸಾ
    0.44
    POSITIVE LOGITS
     Adam
    1.50
    Adam
    1.38
     adam
    1.13
     ADAM
    1.07
    adam
    1.00
     एडम
    0.97
     Adams
    0.91
     آدم
    0.78
    Adams
    0.75
     Eve
    0.70
    Activations Density 0.002%

    No Known Activations