© 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. 35142
    Prev
    Next
    INDEX
    Explanations

    production environment

    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
    റ്റ്‌വർ
    0.41
     montagna
    0.41
    脘
    0.40
     Recognized
    0.39
     couper
    0.38
     réduire
    0.37
     Brake
    0.37
     Ket
    0.36
     venous
    0.36
    ภัณฑ์
    0.36
    POSITIVE LOGITS
    ref
    0.42
     ref
    0.38
    mada
    0.38
    操作系统
    0.36
    ada
    0.35
    да
    0.35
     hogi
    0.35
    జ
    0.35
    Create
    0.35
     сентября
    0.35
    Activations Density 0.001%

    No Known Activations